{ "version": "2.6.3", "generated_at": "2026-08-14T13:05:15+00:00", "mode": "provider_specific_source_expansion_parsers", "summary": { "candidates_seen": 1376, "candidates_after_provider_parsers": 1381, "supported_candidates": 525, "provider_specific_updated": 530, "changed_candidates": 525, "paired_candidates": 5, "promotion_ready": 274, "blocked_runtime_or_hosting": 2, "status_counts": { "token_candidate_ready": 269, "insufficient_token_component": 254, "runtime_or_hosting_not_promoted": 2, "provider_not_supported": 851, "paired_component_candidate_ready": 5 }, "supported_providers": 36, "definition_de": "Anbieterspezifische Zusatzparser normalisieren zusätzliche Quellen nach Modellnamen, Tokenkomponente und Route. Sie erhöhen die Abdeckung, markieren aber weiterhin Prüfbedarf für Region, Vertrag und Modellalias.", "definition_en": "Provider-specific expansion parsers normalize additional sources by model name, token component and route. They improve coverage while keeping region, contract path and model alias under review.", "version": "2.6.3", "generated_at": "2026-08-14T13:05:15+00:00" }, "provider_summary": [ { "provider": "DeepInfra", "candidate_count": 339, "provider_specific_candidates": 339, "promotion_ready": 241, "paired_candidates": 0, "example_models": [ "mistralai/Mixtral-8x22B-Instruct-v0.1", "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "nvidia/NVIDIA-Nemotron-3.5-Lightning", "allenai/olmOCR-7B-1025", "meta-llama/Llama-Guard-3-8B", "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "black-forest-labs/FLUX-2-klein-4b", "deepseek-ai/DeepSeek-V3-0324-Turbo" ] }, { "provider": "Together AI", "candidate_count": 41, "provider_specific_candidates": 41, "promotion_ready": 32, "paired_candidates": 5, "example_models": [ "Kimi K3", "Qwen", "Qwen", "Qwen", "Qwen", "Qwen", "Kimi K3", "Kimi K3" ] }, { "provider": "Fireworks AI", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 1, "paired_candidates": 0, "example_models": [ "Qwen3 8B", "Qwen3 8B" ] }, { "provider": "azure", "candidate_count": 149, "provider_specific_candidates": 149, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "azure/command-r-plus", "azure/eu/gpt-4o-2024-08-06", "azure/eu/gpt-4o-2024-11-20", "azure/eu/gpt-4o-mini-2024-07-18", "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "azure/eu/gpt-4o-realtime-preview-2024-10-01", "azure/eu/gpt-4o-realtime-preview-2024-12-17", "azure/eu/gpt-5-2025-08-07" ] }, { "provider": "bedrock", "candidate_count": 145, "provider_specific_candidates": 145, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "ai21.jamba-1-5-large-v1:0", "ai21.jamba-1-5-mini-v1:0", "ai21.jamba-instruct-v1:0", "amazon.nova-2-multimodal-embeddings-v1:0", "anthropic.claude-3-5-haiku-20241022-v1:0", "anthropic.claude-3-5-sonnet-20240620-v1:0", "anthropic.claude-3-5-sonnet-20241022-v2:0", "anthropic.claude-3-7-sonnet-20240620-v1:0" ] }, { "provider": "openai", "candidate_count": 114, "provider_specific_candidates": 114, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "chatgpt-4o-latest", "gpt-4o-transcribe-diarize", "ft:gpt-3.5-turbo", "ft:gpt-3.5-turbo-0125", "ft:gpt-3.5-turbo-0613", "ft:gpt-3.5-turbo-1106", "ft:gpt-4-0613", "ft:gpt-4o-2024-08-06" ] }, { "provider": "bedrock_converse", "candidate_count": 82, "provider_specific_candidates": 82, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "amazon.nova-lite-v1:0", "amazon.nova-2-lite-v1:0", "amazon.nova-2-pro-preview-20251202-v1:0", "apac.amazon.nova-2-lite-v1:0", "apac.amazon.nova-2-pro-preview-20251202-v1:0", "eu.amazon.nova-2-lite-v1:0", "eu.amazon.nova-2-pro-preview-20251202-v1:0", "us.amazon.nova-2-lite-v1:0" ] }, { "provider": "azure_ai", "candidate_count": 78, "provider_specific_candidates": 78, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "azure_ai/claude-haiku-4-5", "azure_ai/claude-opus-4-5", "azure_ai/claude-opus-4-6", "azure_ai/claude-opus-4-7", "azure_ai/claude-fable-5", "azure_ai/claude-opus-5", "azure_ai/claude-opus-4-8", "azure_ai/claude-opus-4-1" ] }, { "provider": "deepinfra", "candidate_count": 68, "provider_specific_candidates": 68, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "deepinfra/Gryphe/MythoMax-L2-13b", "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B", "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B", "deepinfra/Qwen/QwQ-32B", "deepinfra/Qwen/Qwen2.5-72B-Instruct", "deepinfra/Qwen/Qwen2.5-7B-Instruct", "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "deepinfra/Qwen/Qwen3-14B" ] }, { "provider": "fireworks_ai", "candidate_count": 62, "provider_specific_candidates": 62, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "fireworks-ai-4.1b-to-16b", "fireworks-ai-56b-to-176b", "fireworks-ai-above-16b", "fireworks-ai-moe-up-to-56b", "fireworks-ai-up-to-4b", "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct", "fireworks_ai/accounts/fireworks/models/deepseek-r1", "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528" ] }, { "provider": "gemini", "candidate_count": 47, "provider_specific_candidates": 47, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025", "gemini/gemini-robotics-er-1.5-preview", "gemini/gemini-robotics-er-2-preview", "gemini/gemini-robotics-er-1.6-preview", "gemini/gemini-embedding-001", "gemini/gemini-embedding-2-preview", "gemini/gemini-embedding-2", "gemini/gemini-1.5-flash" ] }, { "provider": "vertex_ai-language-models", "candidate_count": 31, "provider_specific_candidates": 31, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gemini-2.0-flash", "gemini-2.0-flash-001", "gemini-2.0-flash-lite", "gemini-2.0-flash-lite-001", "gemini-2.5-flash", "gemini-2.5-flash-image", "gemini-3-pro-image", "gemini-3-pro-image-preview" ] }, { "provider": "cloudflare", "candidate_count": 30, "provider_specific_candidates": 30, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "cloudflare/@cf/meta/llama-2-7b-chat-fp16", "cloudflare/@cf/meta/llama-2-7b-chat-int8", "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1", "cloudflare/@hf/thebloke/codellama-7b-instruct-awq", "cloudflare/@cf/openai/gpt-oss-120b", "cloudflare/@cf/google/gemma-2b-it-lora", "cloudflare/@cf/meta/llama-3.2-3b-instruct", "cloudflare/@cf/meta/llama-guard-3-8b" ] }, { "provider": "databricks", "candidate_count": 26, "provider_specific_candidates": 26, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "databricks/databricks-claude-3-7-sonnet", "databricks/databricks-claude-haiku-4-5", "databricks/databricks-claude-opus-4", "databricks/databricks-claude-opus-4-1", "databricks/databricks-claude-opus-4-5", "databricks/databricks-claude-sonnet-4", "databricks/databricks-claude-sonnet-4-1", "databricks/databricks-claude-sonnet-4-5" ] }, { "provider": "anthropic", "candidate_count": 24, "provider_specific_candidates": 24, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "claude-haiku-4-5-20251001", "claude-haiku-4-5", "claude-3-7-sonnet-20250219", "claude-3-haiku-20240307", "claude-3-opus-20240229", "claude-4-opus-20250514", "claude-4-sonnet-20250514", "claude-sonnet-4-5" ] }, { "provider": "dashscope", "candidate_count": 24, "provider_specific_candidates": 24, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "dashscope/deepseek-v4-flash", "dashscope/deepseek-v4-flash-0731", "dashscope/deepseek-v4-pro", "dashscope/glm-5.1", "dashscope/glm-5.2", "dashscope/kimi-k2.7-code", "dashscope/qwen-coder", "dashscope/qwen-max" ] }, { "provider": "gmi", "candidate_count": 17, "provider_specific_candidates": 17, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gmi/anthropic/claude-opus-4.5", "gmi/anthropic/claude-sonnet-4.5", "gmi/anthropic/claude-sonnet-4", "gmi/anthropic/claude-opus-4", "gmi/openai/gpt-5.2", "gmi/openai/gpt-5.1", "gmi/openai/gpt-5", "gmi/openai/gpt-4o" ] }, { "provider": "anyscale", "candidate_count": 12, "provider_specific_candidates": 12, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "anyscale/HuggingFaceH4/zephyr-7b-beta", "anyscale/codellama/CodeLlama-34b-Instruct-hf", "anyscale/codellama/CodeLlama-70b-Instruct-hf", "anyscale/google/gemma-7b-it", "anyscale/meta-llama/Llama-2-13b-chat-hf", "anyscale/meta-llama/Llama-2-70b-chat-hf", "anyscale/meta-llama/Llama-2-7b-chat-hf", "anyscale/meta-llama/Meta-Llama-3-70B-Instruct" ] }, { "provider": "baseten", "candidate_count": 11, "provider_specific_candidates": 11, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "baseten/MiniMaxAI/MiniMax-M2.5", "baseten/nvidia/Nemotron-120B-A12B", "baseten/zai-org/GLM-5", "baseten/zai-org/GLM-4.7", "baseten/zai-org/GLM-4.6", "baseten/moonshotai/Kimi-K2.5", "baseten/moonshotai/Kimi-K2-Thinking", "baseten/moonshotai/Kimi-K2-Instruct-0905" ] }, { "provider": "gradient_ai", "candidate_count": 10, "provider_specific_candidates": 10, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gradient_ai/anthropic-claude-3-opus", "gradient_ai/anthropic-claude-3.5-haiku", "gradient_ai/anthropic-claude-3.5-sonnet", "gradient_ai/anthropic-claude-3.7-sonnet", "gradient_ai/deepseek-r1-distill-llama-70b", "gradient_ai/llama3-8b-instruct", "gradient_ai/llama3.3-70b-instruct", "gradient_ai/mistral-nemo-instruct-2407" ] }, { "provider": "vertex_ai", "candidate_count": 9, "provider_specific_candidates": 9, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "vertex_ai/gemini-3-pro-preview", "vertex_ai/gemini-3-flash-preview", "vertex_ai/gemini-3.5-flash", "vertex_ai/gemini-3.6-flash", "vertex_ai/gemini-3.7-flash", "vertex_ai/gemini-3.1-pro-preview", "vertex_ai/gemini-3.1-pro-preview-customtools", "vertex_ai/gemini-embedding-2-preview" ] }, { "provider": "groq", "candidate_count": 9, "provider_specific_candidates": 9, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "groq/llama-3.1-8b-instant", "groq/llama-3.3-70b-versatile", "groq/gemma-7b-it", "groq/meta-llama/llama-prompt-guard-2-22m", "groq/meta-llama/llama-prompt-guard-2-86m", "groq/meta-llama/llama-guard-4-12b", "groq/meta-llama/llama-4-maverick-17b-128e-instruct", "groq/meta-llama/llama-4-scout-17b-16e-instruct" ] }, { "provider": "deepseek", "candidate_count": 8, "provider_specific_candidates": 8, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "deepseek-chat", "deepseek-reasoner", "deepseek/deepseek-chat", "deepseek/deepseek-coder", "deepseek/deepseek-r1", "deepseek/deepseek-reasoner", "deepseek/deepseek-v3", "deepseek/deepseek-v3.2" ] }, { "provider": "cerebras", "candidate_count": 7, "provider_specific_candidates": 7, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "cerebras/llama-3.3-70b", "cerebras/llama3.1-70b", "cerebras/llama3.1-8b", "cerebras/gpt-oss-120b", "cerebras/qwen-3-32b", "cerebras/zai-glm-4.6", "cerebras/zai-glm-4.7" ] }, { "provider": "cohere_chat", "candidate_count": 7, "provider_specific_candidates": 7, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "command-a-03-2025", "command-light", "command-r", "command-r-08-2024", "command-r-plus", "command-r-plus-08-2024", "command-r7b-12-2024" ] }, { "provider": "lemonade", "candidate_count": 5, "provider_specific_candidates": 5, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF", "lemonade/gpt-oss-20b-mxfp4-GGUF", "lemonade/gpt-oss-120b-mxfp-GGUF", "lemonade/Gemma-3-4b-it-GGUF", "lemonade/Qwen3-4B-Instruct-2507-GGUF" ] }, { "provider": "amazon_nova", "candidate_count": 4, "provider_specific_candidates": 4, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "amazon-nova/nova-micro-v1", "amazon-nova/nova-lite-v1", "amazon-nova/nova-premier-v1", "amazon-nova/nova-pro-v1" ] }, { "provider": "volcengine", "candidate_count": 3, "provider_specific_candidates": 3, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "deepseek-v3-2-251201", "glm-4-7-251222", "kimi-k2-thinking-251104" ] }, { "provider": "vertex_ai-embedding-models", "candidate_count": 3, "provider_specific_candidates": 3, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gemini-embedding-001", "gemini-embedding-2-preview", "gemini-embedding-2" ] }, { "provider": "Replicate", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "claude-3.7-sonnet The most intelligent Claude model and the first hybrid reasoning model on the market (claude-3-7-sonnet-20250219)", "deepseek-ai / deepseek-r1 A reasoning model trained with reinforcement learning" ] }, { "provider": "azure_text", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "azure/gpt-3.5-turbo-instruct-0914", "azure/gpt-35-turbo-instruct" ] }, { "provider": "nlp_cloud", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "chatdolphin", "dolphin" ] }, { "provider": "codestral", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "codestral/codestral-2405", "codestral/codestral-latest" ] }, { "provider": "cohere", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "command", "command-nightly" ] }, { "provider": "friendliai", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "friendliai/meta-llama-3.1-70b-instruct", "friendliai/meta-llama-3.1-8b-instruct" ] }, { "provider": "text-completion-openai", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gpt-3.5-turbo-instruct", "gpt-3.5-turbo-instruct-0914" ] } ], "top_ready_candidates": [ { "candidate_id": "4b93b30c483ba7e12b18", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K3", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://www.together.ai/pricing", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.3, "output_usd_per_1m": 1.2, "component": "unknown", "component_usd": null, "confidence": "medium", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Price per 1M tokens Model Input output MiniMax M3 $0.30 $1.20 Kimi K3 $3.00 $15.00 Inkling Small $0.50 $1.20 Qwen3.8-2.4T-A95B $2.50 $6.25 Muse Glimmer 30B $0.35 $1.50 Gemma 4 31B $0.39 $0.97 Kimi K2.7 Code $0.95 $4.00 Qwen3.7-Plus $0.32 $1.28 PrismMLTernary Bonsai 27B 0.00 Inkling $1.00 $4.05 Kimi K2.6 $1.20 $4.50 Qwen3.5 9B $0.17 $0.25 Gemma 3n E4B Instruct $0.06 $0.12 Qwen3.6-Plus $0.50 $3.00 Displayed prices refer to the lowest resolution/duration settings.", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.3, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f972256ef4124ece9686", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 2.5, "output_usd_per_1m": 6.25, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.8-2.4T-A95B | Qwen/Qwen3.8-2.4T-A95B | - | $2.50 | $0.50 | $6.25 | FP4 | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.5, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 6.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b7ac5d6eb7ad433ae47e", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.25, "output_usd_per_1m": 3.75, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.7 Max | Qwen/Qwen3.7-Max | - | $1.25 | - | $3.75 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.25, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.75, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "4c2be2ebcffd00dcaef8", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.5, "output_usd_per_1m": 3.0, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.6 Plus | Qwen/Qwen3.6-Plus | 1000000 | $0.50 | - | $3.00 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.5, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.0, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7960cbeba8524750d0ad", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.17, "output_usd_per_1m": 0.25, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.5 9B | Qwen/Qwen3.5-9B | 262144 | $0.17 | - | $0.25 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.17, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7acd43d91d91a0caa220", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K3", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 3.0, "output_usd_per_1m": 15.0, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Moonshot | Kimi K3 | moonshotai/Kimi-K3 | 1000000 | $3.00 | $0.30 | $15.00 | - | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 15.0, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3908fba4adb9d7b635d3", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K2.7 Code", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.95, "output_usd_per_1m": 4.0, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Moonshot | Kimi K2.7 Code | moonshotai/Kimi-K2.7-Code | 262144 | $0.95 | $0.19 | $4.00 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.95, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 4.0, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "95cd59ef64eab8e1ac2f", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K2.6", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.2, "output_usd_per_1m": 4.5, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Moonshot | Kimi K2.6 | moonshotai/Kimi-K2.6 | 262144 | $1.20 | $0.20 | $4.50 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.2, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 4.5, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "52b9234650033a958a22", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "GLM-5.2", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.4, "output_usd_per_1m": 4.4, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Z.ai | GLM-5.2 | zai-org/GLM-5.2 | 512000 | $1.40 | $0.26 | $4.40 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.4, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 4.4, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5277a1dddd47a2c04a19", "route_provider": "Together AI", "model_provider_inferred": "OpenAI", "model_name": "OpenAI", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.15, "output_usd_per_1m": 0.6, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "OpenAI | GPT-OSS 120B | openai/gpt-oss-120b | 128000 | $0.15 | - | $0.60 | MXFP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.15, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.6, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c46145d1e41faa9a1fa1", "route_provider": "Together AI", "model_provider_inferred": "OpenAI", "model_name": "OpenAI", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.05, "output_usd_per_1m": 0.2, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "OpenAI | GPT-OSS 20B | openai/gpt-oss-20b | 128000 | $0.05 | - | $0.20 | MXFP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.05, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e39ccdb4243034e1df0d", "route_provider": "Together AI", "model_provider_inferred": "DeepSeek", "model_name": "DeepSeek", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.74, "output_usd_per_1m": 3.48, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "DeepSeek | DeepSeek-V4-Pro | deepseek-ai/DeepSeek-V4-Pro | 512000 | $1.74 | $0.20 | $3.48 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.74, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.48, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7b2f4afae0ec0ce4b186", "route_provider": "Together AI", "model_provider_inferred": "DeepSeek", "model_name": "DeepSeek", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.14, "output_usd_per_1m": 0.28, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "DeepSeek | DeepSeek-V4-Flash-0731 | deepseek-ai/DeepSeek-V4-Flash-0731 | 1000000 | $0.14 | $0.03 | $0.28 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.14, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.28, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0cfd3660e1ada089c955", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "Nemotron 3 Ultra 550B A55B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.6, "output_usd_per_1m": 3.6, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "NVIDIA | Nemotron 3 Ultra 550B A55B | nvidia/nemotron-3-ultra-550b-a55b | 512300 | $0.60 | $0.20 | $3.60 | NVFP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.6, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.6, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0555467c0415bc0d5d37", "route_provider": "Together AI", "model_provider_inferred": "Meta / Llama", "model_name": "Llama 3.3 70B Instruct Turbo", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.04, "output_usd_per_1m": 1.04, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Meta | Llama 3.3 70B Instruct Turbo | meta-llama/Llama-3.3-70B-Instruct-Turbo | 131072 | $1.04 | - | $1.04 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.04, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.04, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3b4a65007c6649851f3b", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.3, "output_usd_per_1m": 0.3, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen 2.5 7B Instruct Turbo | Qwen/Qwen2.5-7B-Instruct-Turbo | 32768 | $0.30 | - | $0.30 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.3, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.3, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "594f5f070c0873e46d3b", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 4 31B Instruct", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.39, "output_usd_per_1m": 0.97, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Google | Gemma 4 31B Instruct | google/gemma-4-31B-it | 262144 | $0.39 | - | $0.97 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.39, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.97, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e8ddc65465168f1075fe", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 4 31B Instruct", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.28, "output_usd_per_1m": 0.86, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Pearl AI | Gemma 4 31B Instruct | pearl-ai/gemma-4-31b-it | 32000 | $0.28 | - | $0.86 | INT8 | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.28, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.86, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "25684b1897dcf7790aa7", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "Cogito v2.1 671B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.25, "output_usd_per_1m": 1.25, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Deepcogito | Cogito v2.1 671B | deepcogito/cogito-v2-1-671b | 163840 | $1.25 | - | $1.25 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.25, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8ab8d00b498aaeb8a971", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.32, "output_usd_per_1m": 1.28, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.7 Plus | Qwen/Qwen3.7-Plus | 1000000 | $0.32 | - | $1.28 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.32, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.28, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b867c1faafa399f31c22", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 3N E4B Instruct", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.06, "output_usd_per_1m": 0.12, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Google | Gemma 3N E4B Instruct | google/gemma-3n-E4B-it | 32768 | $0.06 | - | $0.12 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.06, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.12, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "80e77080a9f1f39d35e0", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "LFM2.5-8B-A1B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.03, "output_usd_per_1m": 0.12, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "LiquidAI | LFM2.5-8B-A1B | LiquidAI/LFM2.5-8B-A1B | 32768 | $0.03 | - | $0.12 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.03, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.12, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2d21a13ef38e516f81d0", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "Muse Glimmer 30B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.35, "output_usd_per_1m": 1.5, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Meta | Muse Glimmer 30B | meta-models/Muse-Glimmer-30B | 131072 | $0.35 | $0.04 | $1.50 | FP8 | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.35, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.5, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e2ce6f893b6317c7a90f", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 4 31B IT", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.39, "output_usd_per_1m": 0.97, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Google | Gemma 4 31B IT | google/gemma-4-31B-it | 262144 | $0.39 | $0.97", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.39, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.97, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1260d46b0472dba8be84", "route_provider": "Together AI", "model_provider_inferred": "Meta / Llama", "model_name": "Llama Guard 4 12B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.2, "output_usd_per_1m": 0.2, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Meta | Llama Guard 4 12B | meta-llama/Llama-Guard-4-12B | 1048576 | $0.20 | $0.20", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.2, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b57fbbd07d74bdde2411", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen Qwen3.5 9B Qwen/Qwen3.5-9B 262144", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.17, "output_usd_per_1m": 0.25, "component": "unknown", "component_usd": null, "confidence": "medium", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Organization Model name API model string Context length Input pricing (per 1M tokens) Output pricing (per 1M tokens) Qwen Qwen3.5 9B Qwen/Qwen3.5-9B 262144 $0.17 $0.25 Google Gemma 4 31B IT google/gemma-4-31B-it 262144 $0.39 $0.97 Minimax Minimax M3 MiniMaxAI/MiniMax-M3 524288 $0.30 $1.20 Moonshot Kimi K3 moonshotai/Kimi-K3 1000000 $3.00 $15.00 Moonshot Kimi K2.7 Code moonshotai/Kimi-K2.7-Code 262144 $0.95 $4.00 Moonshot Kimi K2.6 moonshotai/Kimi-K2.6 262144 $1.20 $4.50 ​ Vision model examples L", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.17, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ffb6f156b9ddbbd02684", "route_provider": "Together AI", "model_provider_inferred": "Meta / Llama", "model_name": "Meta Llama Guard 4 12B meta-llama/Llama-Guard-4-12B 1048576", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": 0.2, "component": "unknown", "component_usd": null, "confidence": "medium", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "​ Moderation models Organization Model name API model string Context length Input pricing (per 1M tokens) Output pricing (per 1M tokens) Meta Llama Guard 4 12B meta-llama/Llama-Guard-4-12B 1048576 $0.20 $0.20 Was this page helpful?", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "output_tokens", "amount_usd": 0.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "588c0629ac203f9d7b59", "route_provider": "Fireworks AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen3 8B", "source_id": "fireworks_pricing_page", "source_type": "official_primary", "source_url": "https://fireworks.ai/pricing", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.1, "output_usd_per_1m": null, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Fireworks AI mit gezieltem Parser für Tokenpreis-Tabellen und Modellzeilen.", "notes_en": "Fireworks AI as additional inference provider. HTML candidates are not treated as confirmed until component mapping is clear.", "raw_snippet": "Qwen3 8B | $0.1", "provider_specific_parser": "fireworks_token_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.1, "field": "input_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "Fireworks AI", "provider_specific_note_de": "Fireworks-AI-Kandidaten werden als zusätzliche direkte Anbieterroute geführt, sofern Tokenkomponente und Preiswert plausibel sind.", "provider_specific_note_en": "Fireworks AI candidates are treated as an additional direct provider route when component and amount are plausible.", "provider_specific_model_normalized": true, "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1ed9c30e0f035342ad6b", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mixtral-8x22B-Instruct-v0.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 65.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mixtral-8x22B-Instruct-v0.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"This is the instruction fine-tuned version of Mixtral-8x22B - the latest and largest mixture of experts large language model (LLM) from Mistral AI. This state of the art machine learning model uses a mixture 8 of experts (MoE) 22b models. During inference 2 experts are selected. This architecture allows large models to be fast and cheap at inference.\", \"cover_img", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 65.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a2a69e99704b928d74cd", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B/cover_ima", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f88b5c0dea6013c6c131", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-3.5-Lightning", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 8.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-3.5-Lightning\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"NVIDIA Nemotron 3.5 Lightning is NVIDIA's fastest open model for always-on agents and high-volume specialized tasks. It delivers a substantial leap in agentic capability over its predecessor Nemotron 3 Nano, with up to 4x higher throughput on a 1M-token context.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/nvidia/NVIDIA-Nemotron-3.5-Lightning/cover_imag", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 8.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2d8514b98e4a8d64910e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "allenai/olmOCR-7B-1025", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 14.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"allenai/olmOCR-7B-1025\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"olmOCR is a specialized AI tool that converts PDF documents into clean, structured text while preserving important formatting and layout information. What makes olmOCR particularly valuable for developers is its ability to handle challenging PDFs that traditional OCR tools struggle with—including complex layouts, poor-quality scans, handwritten text, and documents with mixed co", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 14.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1834f806824b0ced5e39", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-Guard-3-8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-Guard-3-8B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama Guard 3 is a Llama-3.1-8B pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) and in LLM responses (response classification). It acts as an LLM – it generates text in its output that indicates whether a given prompt or response is safe or unsafe, an", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9f69fb11f24c1aa19376", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 70.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-R1-Distill-Llama-70B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-R1-Distill-Llama-70B is a highly efficient language model that leverages knowledge distillation to achieve state-of-the-art performance. This model distills the reasoning patterns of larger models into a smaller, more agile architecture, resulting in exceptional results on benchmarks like AIME 2024, MATH-500, and LiveCodeBench. With 70 billion parame", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 70.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "96431c2d3ec9ac744801", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V3-0324-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 100.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V3-0324-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"openai\", \"tools\", \"b200\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 0.0001, \"cents_per_output_token\": 0.0003, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_write\": null, \"rate_per_service_tier_priority\": null, \"rate_per_service_tier_flex\": null, \"rate_per_e", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 100.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "038fcfe4a6b8dcdfa0fb", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Devstral-Small-2505", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 6.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Devstral-Small-2505\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Devstral is an agentic LLM for software engineering tasks. Devstral excels at using tools to explore codebases, editing multiple files and power software engineering agents. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Devstral-Small-2505/cover_image.7f4d4eef714d466c1287bec36616939a0d8f255b1ed36d80b17410eae66bdbaf.webp\", \"tags\": [\"openai\", \"cc-nativ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 6.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5a6d6a20aa4af1d3b6d0", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-3-Embed-1B-BF16", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-3-Embed-1B-BF16\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"Nemotron-3-Embed-1B-BF16 is a compact multilingual text embedding model from NVIDIA, pruned and distilled from Ministral-3 to ~1B parameters, that maps text into 2048-dimensional dense vectors for retrieval and semantic similarity. Spanning 34 languages, it delivers state-of-the-art quality among similarly sized models for RAG and multilingual question-answering while keeping co", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "50ba85eb89d6def91a79", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "bigcode/starcoder2-15b-instruct-v0.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 15.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"bigcode/starcoder2-15b-instruct-v0.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"We introduce StarCoder2-15B-Instruct-v0.1, the very first entirely self-aligned code Large Language Model (LLM) trained with a fully permissive and transparent pipeline. Our open-source pipeline uses StarCoder2-15B to generate thousands of instruction-response pairs, which are then used to fine-tune StarCoder-15B itself without any human annotations or distilled d", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 15.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "591c011b3bb1035c3f28", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K3", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 285.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K3\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Kimi K3 is Moonshot AI's 2.8T-parameter open-weight multimodal reasoning model. Built for complex coding, knowledge work, and long-horizon agentic workflows, it excels at navigating large repositories, calling tools, debugging, and iterating on images, logs, tests, and runtime feedback. Its architecture relies on KDA and Attention Residuals for computational efficiency.\", \"cover_im", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 285.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5771ea5d5ed179f02085", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo/cover_image.cad8905e3734dbb35efcadd521b580b60745e251dfb88235f96d2bc3aa397f", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "53ac0ce05a14279aa989", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "zai-org/GLM-5.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 105.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"zai-org/GLM-5.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"GLM-5.1 is Z-AI's next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/zai-org/GLM-5.1", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 105.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7a30706bcb6c88ea4c3b", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "inworld-ai/inworld-tts-1.5-mini", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2500.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"inworld-ai/inworld-tts-1.5-mini\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"Fast multilingual text-to-speech model by Inworld AI with 130+ preset voices across 15 languages. Supports voice cloning, word-level timestamps, and streaming. Optimized for low-latency applications with <130ms time-to-first-audio.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/inworld-ai/inworld-tts-1.5-mini/cover_image.4949ffe99638b5877cd72f411b5d9603d5b3b084f", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2500.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8b5873f9fb1b0b3db8bf", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "allenai/olmOCR-7B-0725-FP8", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"allenai/olmOCR-7B-0725-FP8\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"olmOCR is a specialized AI tool that converts PDF documents into clean, structured text while preserving important formatting and layout information. What makes olmOCR particularly valuable for developers is its ability to handle challenging PDFs that traditional OCR tools struggle with—including complex layouts, poor-quality scans, handwritten text, and documents with mixe", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "eefcbb7ab8885d7019d8", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-4B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-4B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-4B is a mid-size model from Alibaba's Qwen3.5 series that delivers a strong balance of performance and efficiency. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Well-suited for complex reasoning, code generation, and agentic applications.\", \"cover_img_url\": \"https://shared.deepinfra.c", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "15c90c8eab786bfae3e0", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-3.2-90B-Vision-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 35.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-3.2-90B-Vision-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks. It offers unparalleled accuracy in image captioning, visual question answering, and advanced image-text comprehension. Pre-trained on vast multimodal datasets and fine-tuned with human feedback, the Llama 90B Vi", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 35.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "d95d085a137ec0f06b10", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "cognitivecomputations/dolphin-2.9.1-llama-3-70b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 35.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"cognitivecomputations/dolphin-2.9.1-llama-3-70b\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Dolphin 2.9.1, a fine-tuned Llama-3-70b model. The new model, trained on filtered data, is more compliant but uncensored. It demonstrates improvements in instruction, conversation, coding, and function calling abilities.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/cognitivecomputations/dolphin-2.9.1-llama-3-70b/cover_image.4192f8825b0d9ba661", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 35.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "d817dfd01b73ad33af24", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/QVQ-72B-Preview", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/QVQ-72B-Preview\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities. QVQ-72B-Preview has achieved remarkable performance on various benchmarks. It scored a remarkable 70.3% on the Multimodal Massive Multi-task Understanding (MMMU) benchmark\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/QVQ-72B-Preview/co", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b8b4868f4ed79e0c6a79", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Embedding-8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Embedding-8B\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-E", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a94e82c6abb0f789d41e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-R1-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 100.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-R1-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"We introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-R1-Turbo/cover_image.ef6fed0befbf14b90f0be63a8a12af864029c2fe7178cdab32fc801f79223e48.webp\", \"tags\": [\"openai\", \"tools\", \"b200", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 100.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2fa4b4d99cf1f3ccb02d", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/embeddinggemma-300m", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 0.19999999999999998, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/embeddinggemma-300m\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"EmbeddingGemma is a 300M parameter multilingual open embedding model from Google DeepMind, designed for efficient deployment even on low-resource devices, producing high-quality text vector representations for tasks such as search, classification, clustering, and semantic similarity.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/embeddinggemma-300m/cover_image.6be517", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.19999999999999998, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e7fdb8eb71c1cb988482", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Meta-Llama-3-8B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Meta-Llama-3-8B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meta developed and released the Meta Llama 3 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8 and 70B sizes.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3-8B-Instruct/cover_image.9ea753fd36aabfbca4939ee488b859e08e95c4626ffff71ec3a385be66b1d3ba.webp\", \"tags\": [\"open", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "77adf415b64efa6b1d13", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-TTS-VoiceDesign", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2000.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-TTS-VoiceDesign\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"● Qwen3-TTS-VoiceDesign is a voice design variant of Qwen3-TTS by Alibaba's Qwen team. Instead of selecting from preset voices, you describe the voice you want in natural language — and the model generates speech in that voice. Key capabilities: - Natural language voice control — describe any", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2000.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "364fa8a9d80c99a0fbaa", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-Content-Safety-3.5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-Content-Safety-3.5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-tr", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5ec73e23030d94c06c6b", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-2B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-2B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-2B is a compact yet capable model from Alibaba's Qwen3.5 series. It features a 262K token context window, support for 201 languages, thinking/reasoning mode, and tool calling for agentic workflows. A strong choice for prototyping, fine-tuning, and efficient multilingual deployments.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3.5-2B/cover_image.c3dfd7ec6ae", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5b631bc3bbbbbab272af", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/QwQ-32B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 15.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/QwQ-32B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"QwQ is the reasoning model of the Qwen series. Compared with conventional instruction-tuned models, QwQ, which is capable of thinking and reasoning, can achieve significantly enhanced performance in downstream tasks, especially hard problems. QwQ-32B is the medium-sized reasoning model, which is capable of achieving competitive performance against state-of-the-art reasoning models, e.g.,", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 15.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7b6ca13297eedf242718", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-fable-5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1000.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-fable-5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Claude Fable 5 is Anthropic's next generation of intelligence for the hardest knowledge work and coding problems. It works independently for longer than any prior generally available Claude model: run it in an agent harness and it can work for days at a time, planning across stages, delegating to sub-agents, and checking its own work.\", \"cover_img_url\": \"https://shared.deepin", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1000.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7cc13b14c7e0b283bcac", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-235B-A22B-Thinking-2507", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 23.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-235B-A22B-Thinking-2507\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3-235B-A22B-Thinking-2507 is the Qwen3's new model with scaling the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-235B-A22B-Thinking-2507/cover_image.2b87c6645946388f890b18b46894e32d140913d73154eb6ae428e378916853c3.webp\", \"tags\": [\"openai\", \"tools\", \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 23.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "314207d5126ad109a59e", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemini-3.1-flash-lite", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemini-3.1-flash-lite\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Bring any idea to life with state-of-the-art reasoning to help you learn, build, and plan anything. Best for high-volume tasks that need efficiency and intelligence.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemini-3.1-flash-lite/cover_image.525a90a425f2f2c1855b66bdf94fe2025c945e45e2c724d78a4a4c8d67e1d034.webp\", \"tags\": [\"no-free-anon\", \"cc-native\", \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9f06b811dd31dc128153", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2.5-7B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 4.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2.5-7B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The 7 billion parameter Qwen2.5 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen2.5-7B-Instruct/cover_image.f1f5fd736a4e6bd9c33961de8cc74acf677c130545e1beece8cd0b06c3c69fea.webp\", \"tags\": [\"openai\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 4.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "db09dd90f3b1f691a85c", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3.3-70B-Euryale-v2.3", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 85.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3.3-70B-Euryale-v2.3\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"L3.3-70B-Euryale-v2.3 is a model focused on creative roleplay from Sao10k\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Sao10K/L3.3-70B-Euryale-v2.3/cover_image.3edd53f864ebe24fe632eaf96361233e514097255cc7ab9bb0d96876aece9a7b.webp\", \"tags\": [\"json\", \"openai\", \"non-reasoning\", \"structured-output\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 85.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "6dc004dd8bb7a986d981", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "NovaSky-AI/Sky-T1-32B-Preview", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 12.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"NovaSky-AI/Sky-T1-32B-Preview\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"This is a 32B reasoning model trained from Qwen2.5-32B-Instruct with 17K data. The performance is on par with o1-preview model on both math and coding.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/NovaSky-AI/Sky-T1-32B-Preview/cover_image.50c7308479b460765575b02e9b060064817da5b62453b03eb284ddeb1aaecb79.webp\", \"tags\": [\"openai\"], \"pricing\": {\"short\": null, \"ful", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 12.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c59ca6f74c4080a436bc", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemini-3.5-flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 150.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemini-3.5-flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemini 3.5 Flash delivers near-Pro intelligence at Flash-tier cost and speed: Pro-level coding proficiency, parallel agentic execution, all at a much lower price.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemini-3.5-flash/cover_image.db12bcf5eae7b129cd2d01bf80aafc0ae718c0c3688b07a218cfdc674d6b7e6b.webp\", \"tags\": [\"json\", \"openai\", \"multimodal\", \"no-free-an", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 150.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "29cd389f0434915b0b7d", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-TTS", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2000.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-TTS\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \" Qwen3-TTS is an advanced text-to-speech model by Alibaba's Qwen team, delivering stable, expressive, and low-latency speech generation across 10 languages. Key capabilities: - 9 preset voices — Vivian, Serena, Uncle_Fu, Dylan, Eric,", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2000.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "841db09eb1bdd329cf90", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-3-Embed-8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-3-Embed-8B\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"Nemotron-3-Embed-8B is a multilingual text embedding model from NVIDIA, based on Ministral-3-8B, that maps text into 4096-dimensional dense vectors for retrieval and semantic similarity. Spanning 34 languages, it targets multilingual RAG and question-answering over large corpora and achieves state-of-the-art results on the RTEB leaderboard.\", \"cover_img_url\": \"https://shared.deepinfr", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "71eeca31884a3a4f2a9a", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-30B-A3B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 12.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-30B-A3B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-30B-A3B/cove", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 12.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0627d0f986fef7087348", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Maverick, a 17 billion parameter model with 128 experts\", \"cover_img_url\": \"https://shared.deepinfra.com", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "bf4e8b78b1d6bcdb187c", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo/cover_image.72a176f3bc06874ecc847a5743722cfdcbffa23e9d69fdd5722a0c7a5ebc", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "16bee516a3f06aaac8a2", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 8.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.\", \"cover_img_url\": \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 8.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "bc341274a3217b401b02", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "nvidia/llama-nemotron-rerank-vl-1b-v2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/llama-nemotron-rerank-vl-1b-v2\", \"type\": \"reranker\", \"reported_type\": \"reranker\", \"description\": \"The llama-nemotron-rerank-vl-1b-v2 is a 1.7B parameter multimodal reranking model designed to evaluate and order the relevance of document images and text against specific user queries. It excels at understanding complex visual content like charts, tables, and infographics.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/nvidia/llama-nemotron-rerank-vl-1b-v2/cover_imag", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0e9d8365de4d39839619", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Nemotron 3 Nano Omni is an open multimodal model built on a hybrid Mixture-of-Experts (MoE) architecture, engineered for high efficiency and strong accuracy across image, video, audio, and text inputs. It powers always-on sub-agents for computer use, document intelligence, and audio-video understanding—replacing fragmented vision, speech, and language pip", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e9833df946dc3791966d", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3-8B-Lunaris-v1-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 4.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3-8B-Lunaris-v1-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"json\", \"openai\", \"non-reasoning\", \"structured-output\", \"flex\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 4e-06, \"cents_per_output_token\": 5e-06, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_write\": null, \"rate_per_service_tier_priority\": null, \"rate_per_service", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 4.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5d3bd16dca1f86190b82", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.7-Max", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 250.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.7-Max\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The largest and most capable in the Qwen3.7 series. Qwen3.7 is a next‑generation flagship model designed for the agent‑centric.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3.7-Max/cover_image.ca11accb7c4e1cd630f411727764a17290246e5c6e7be1ec26cecd6b98427818.webp\", \"tags\": [\"no-free-anon\", \"json\", \"cc-native\", \"non-reasoning\", \"structured-output\", \"tools\", \"openai\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 250.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3fd00f57d8767a36eea5", "route_provider": "DeepInfra", "model_provider_inferred": "xAI", "model_name": "MiniMaxAI/MiniMax-M3", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 28.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"MiniMaxAI/MiniMax-M3\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/MiniMaxAI/MiniMax-M3/cover_image.811cbc3e080f92da03204dc6921c5d48b7b9b3cedf5fdf85f1228a9b1a6161c5.webp\", \"tags\": [\"openai\", \"cc-native\", \"multimodal\", \"tools\", \"reasoning\", \"json\", \"input-video\", \"flex\", \"structure", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 28.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "29fcacfeafaf90adde22", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-32B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 8.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-32B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-32B/cover_image.", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 8.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f58ead1bb6cbce116ab9", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"NVIDIA Nemotron 2 Nano VL extends the Nemotron family into multi-modal reasoning and document intelligence. This auto-regressive vision-language model enables multi-image reasoning, video understanding, visual Q&A and document analysis and summarization. Optimized for enterprise AI workflows, it powers multimodal agentic systems such as visual copilots, document ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "974f52dc9b154b0d8635", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "KoboldAI/LLaMA2-13B-Tiefighter", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 10.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"KoboldAI/LLaMA2-13B-Tiefighter\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"LLaMA2-13B-Tiefighter is a highly creative and versatile language model, fine-tuned for storytelling, adventure, and conversational dialogue. It combines the strengths of multiple models and datasets, including retro-rodeo and choose-your-own-adventure, to generate engaging and imaginative content. With its ability to improvise and adapt to different styles and formats,", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 10.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "bf5bb5691ef358d10e5f", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-7B-Instruct-v0.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-7B-Instruct-v0.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.1/cover_image.cdb70679749ff93eb56b8480215bb8cd1382cbeffcec00a06bdb0145be9ef511.webp\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a948977d5fc0c4cbb0e6", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-Guard-4-12B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 18.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-Guard-4-12B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 18.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "17959f061deb979fd41a", "route_provider": "DeepInfra", "model_provider_inferred": "xAI", "model_name": "MiniMaxAI/MiniMax-M2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.400000000000002, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"MiniMaxAI/MiniMax-M2\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"MiniMax-M2 is a Mini model built for Max coding & agentic workflows with just 10 billion activated parameters\", \"cover_img_url\": \"https://shared.deepinfra.com/models/MiniMaxAI/MiniMax-M2/cover_image.5474fbcd5f4eaf2d5123e79bb02291d98597f9b2847a1e2bce182ea836d4d9d5.webp\", \"tags\": [\"openai\", \"cc-native\", \"tools\", \"json\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.400000000000002, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "04eb09f616e40a38073d", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-4-sonnet", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 330.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-4-sonnet\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Anthropic's mid-size model with superior intelligence for high-volume uses in coding, in-depth research, agents, & more.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-4-sonnet/cover_image.abb94fa3840b2f233747c56e1877ad22a139fad1fdd205914141f03a786ca74c.webp\", \"tags\": [\"ocr\", \"openai\", \"tools\", \"multimodal\", \"no-free-anon\", \"json\", \"non-reasoning\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 330.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ae13015ddeb366afc9f1", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-0.8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-0.8B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-0.8B is Alibaba's smallest model in the Qwen3.5 series, featuring a hybrid Gated Delta Networks and sparse Mixture-of-Experts architecture. Despite its compact size, it supports a 262K token context window, 201 languages, thinking/reasoning mode, and tool calling. Ideal for edge deployments, resource-constrained environments, and lightweight inference tasks.\", \"cover_img_url", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "cc901c8f6aaac61b3476", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "zai-org/GLM-4.5-Air", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"zai-org/GLM-4.5-Air\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5 models unify reasoning, coding, and intelligent agent capabilities to meet the complex demands of intel", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ac28e842a9c7efd59a0f", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V4-Flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 9.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V4-Flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-V4-Flash/cover_image.816346e8186ef1652de4efda60bee06c74b36", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 9.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7268abd86e030cc77561", "route_provider": "DeepInfra", "model_provider_inferred": "xAI", "model_name": "MiniMaxAI/MiniMax-M2.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"MiniMaxAI/MiniMax-M2.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"MiniMax-M2.1 is a model optimized specifically for robustness in coding, tool use, instruction following, and long-horizon planning. From automating multilingual software development to executing complex, multi-step office workflows, MiniMax-M2.1 empowers developers to build the next generation of autonomous applications—all while being fully transparent, controllable, and acce", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c8054024c01aeba967bc", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-1.1-7b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 7.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-1.1-7b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma is an open-source model designed by Google. This is Gemma 1.1 7B (IT), an update over the original instruction-tuned Gemma release. Gemma 1.1 was trained using a novel RLHF method, leading to substantial gains on quality, coding capabilities, factuality, instruction following and multi-turn conversation quality.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/goog", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 7.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0670380e7ffb7a5d213b", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-9B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 10.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-9B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.\", \"cover_img_url\": \"https://shared.deepinfr", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 10.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "46d9f4eafc9da3dcaf11", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "ByteDance/Seed-1.8", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"ByteDance/Seed-1.8\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/ByteDance/Seed-1.8/cover_image.cb600a23d0b2ba7499346c021edb1097501a09cf2a6ee4f0641fd76180624182.webp\", \"tags\": [\"openai\", \"tools\", \"reasoning\", \"multimodal\", \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "4d54d22364e7fec6f3e5", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "microsoft/WizardLM-2-7B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"microsoft/WizardLM-2-7B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"WizardLM-2 7B is the smaller variant of Microsoft AI's latest Wizard model. It is the fastest and achieves comparable performance with existing 10x larger open-source leading models\", \"cover_img_url\": \"https://shared.deepinfra.com/models/microsoft/WizardLM-2-7B/cover_image.305876b2901f4833a14d17e09a3876b59ca7561b73017518970a75643fe9ff69.webp\", \"tags\": [\"openai\"], \"pricing\": {\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "64af68dae3eff4a8ef72", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "google/veo-3.0", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "output_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/veo-3.0\", \"type\": \"text-to-video\", \"reported_type\": \"text-to-video\", \"description\": \"Veo 3 is a state-of-the-art text-to-video model from Google that generates high-fidelity, cinematic videos with synchronized audio from a simple text prompt. It excels at creating realistic and imaginative scenes with a deep understanding of natural language and visual dynamics.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/veo-3.0/cover_image.4817ee203a8eeda7540d449add885", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "output_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2ff731865022e03477d7", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "openbmb/MiniCPM-Llama3-V-2_5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 34.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"openbmb/MiniCPM-Llama3-V-2_5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"openai\", \"cc-native\", \"multimodal\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 3.4e-05, \"cents_per_output_token\": 3.4e-05, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_write\": null, \"rate_per_service_tier_priority\": null, \"rate_per_service_tier_flex\": null, \"rate", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 34.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1252ddfcdd2e7855c224", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V3.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V3.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f5b34323111c3025fffe", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "google/veo-3.0-fast", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "output_tokens", "component_usd": 15.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/veo-3.0-fast\", \"type\": \"text-to-video\", \"reported_type\": \"text-to-video\", \"description\": \"Veo 3 Fast is a speed-optimized version of the Veo 3 model, designed for rapid video creation. While maintaining high quality, it delivers results in a fraction of the time, making it ideal for quick iterations and dynamic content generation.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/veo-3.0-fast/cover_image.d0ccd94f2e9b613048b22e9323bb73ac954e8bfb74ca6dacc711b3cf", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "output_tokens", "amount_usd": 15.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "248e3917690093c54409", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "nvidia/llama-nemotron-embed-vl-1b-v2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/llama-nemotron-embed-vl-1b-v2\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The llama-nemotron-embed-vl-1b-v2 is a high-performance multimodal embedding model designed to transform text queries and document images into dense vector representations for advanced retrieval systems. It excels at understanding complex visual content like charts, tables, and infographics.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/nvidia/llama-nemotron-embed", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3935a193e60bcbcd6678", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "sesame/csm-1b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 700.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"sesame/csm-1b\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/sesame/csm-1b/cover_image.e79911aabdd060a3939b5188731bb689a92a627c7e9a0d6e35574937707997ab.we", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 700.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a061be2893ae71d3b155", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3-70B-Euryale-v2.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 70.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3-70B-Euryale-v2.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Euryale 70B v2.1 is a model focused on creative roleplay from Sao10k\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Sao10K/L3-70B-Euryale-v2.1/cover_image.f092eab9d5027b46b76339eae05a40e0235e8481e7e0da0776fe53a509f37957.webp\", \"tags\": [\"openai\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 7e-05, \"cents_per_out", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 70.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "761d52596f76dba5b710", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-VL-30B-A3B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 15.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-VL-30B-A3B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\", \"cover_img_url\": \"h", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 15.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8d2457f07d3c3f6032d5", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V3.1-Terminus", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V3.1-Terminus\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-V3.1 Terminus is an update to DeepSeek V3.1 that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's performance in coding and search agents. It is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2f8ef92f8a66708aa95a", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "inclusionAI/Ling-3.0-flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 6.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"inclusionAI/Ling-3.0-flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The model prioritizes token efficiency and agentic inference at production scale, stretching what developers can achieve within limited token, latency, and serving-cost budgets.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/inclusionAI/Ling-3.0-flash/cover_image.8c2d5d705a06405d51730ae3351ef669c3f30559f039d49e2f1dc589bfbca9fb.webp\", \"tags\": [\"cc-native\", \"openai\",", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 6.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9bcc77790927ba6cc933", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-sonnet-4-6", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 300.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-sonnet-4-6\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-sonnet-4-6/cover_image.eb8fe98327537b626c115e8e17b5670154e60083b82bcf56821263f376bb8490.webp\", \"tags\": [\"multimodal\", \"cc-native\", \"reasoning\", \"json\", \"structured-output\", \"tools\", \"ocr\", \"no", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 300.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2c8b33b9266c2cd7f374", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-Prover-V2-671B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-Prover-V2-671B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start training procedure begins by prompting DeepSeek-V3 to decompose complex problems into a series of subgoals. The proofs of resolved subgoals are s", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "65c81d1c1b8a4f47444b", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V3.2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 26.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V3.2\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that reduces training and inference cost while preserving quality in long-context scenarios. A scalable reinforcement learning post-training", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 26.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c893a442f9248a78c834", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "zai-org/GLM-4.7-Flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 6.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"zai-org/GLM-4.7-Flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/zai-org/GLM-4.7-Flash/cover_image.3c0c7f830a57de23a3f15107b442a12b8a434b922e45a734dd90791583afd960.webp\", \"tags\": [\"openai\", \"tools\", \"reasonin", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 6.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8a75acf7fe8ace8fb6d5", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2.5-Coder-32B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 6.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2.5-Coder-32B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). It has significant improvements in code generation, code reasoning and code fixing. A more comprehensive foundation for real-world applications such as Code Agents. Not only enhancing coding capabilities but also maintaining its strengths in mathematics and gene", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 6.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "61b88c9223d5fb4145ba", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Coder-30B-A3B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 7.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Coder-30B-A3B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3-Coder-30B-A3B-Instruct is a high-performance code generation model optimized for agentic coding and complex programming tasks. With 30.5B total parameters and 3.3B activated through Mixture-of-Experts architecture, it delivers exceptional efficiency. The model features native support for 256K token context (extendable to 1M), making it ideal for repository-scal", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 7.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9e5c51c1d90b9d9e645c", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-235B-A22B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 18.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-235B-A22B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-235B-A22B/", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 18.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2998ef8ee45315398334", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-3-12b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-3-12b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2\", \"cover_img_url\": \"https://shared.d", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "308eee47b6dc53ba6e96", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "ByteDance/Seedance-1.5-Pro", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 120.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"ByteDance/Seedance-1.5-Pro\", \"type\": \"text-to-video\", \"reported_type\": \"text-to-video\", \"description\": \"ByteDance's Seedance 1.5 Pro is a professional video model using V2A native generation for integrated, synced audio-visual output, enhancing efficiency of professional video creation.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/ByteDance/Seedance-1.5-Pro/cover_image.3a04465c7b080e6a46070c9ea13aa88e223bb62c44ee8d822f157834af15805d.webp\", \"tags\": [\"no-free-anon\", \"ope", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 120.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "19aebd7302702aec831c", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "microsoft/WizardLM-2-8x22B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 48.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"microsoft/WizardLM-2-8x22B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to those leading proprietary models.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/microsoft/WizardLM-2-8x22B/cover_image.395b63e0d661def89bf43c88976a699b066f69208b3b58ae5cc2663693033ee8.webp\", \"tags\": [\"openai\", \"json\", \"structured-output\"], \"pri", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 48.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "794df9c2f03726e1c468", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Max", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 120.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Max\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The latest flagship model in the Qwen family. State-of-the-art results across a comprehensive suite of benchmarks — including knowledge, reasoning, coding, instruction following, human preference alignment, agent tasks, and multilingual understanding.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-Max/cover_image.3c5c67a21ba4b7489e6d6531bd6b115793411327124fb93ac886a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 120.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9e39a4903af4dcc2a945", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2.5-72B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 36.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2.5-72B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilin", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 36.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5797f63abb9b91c01f91", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemini-2.5-pro", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 125.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemini-2.5-pro\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemini 2.5 Pro is Google's the most advanced thinking model, designed to tackle increasingly complex problems. Gemini 2.5 Pro leads common benchmarks by meaningful margins and showcases strong reasoning and code capabilities. Gemini 2.5 models are thinking models, capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accura", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 125.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "29508febc4645d31d340", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-3.2-11B-Vision-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 34.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-3.2-11B-Vision-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama 3.2 11B Vision is a multimodal model with 11 billion parameters, designed to handle tasks combining visual and textual data. It excels in tasks such as image captioning and visual question answering, bridging the gap between language generation and visual reasoning. Pre-trained on a massive dataset of image-text pairs, it performs well in complex, high-a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 34.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "653960d8487c35ebd10e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3-8B-Lunaris-v1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3-8B-Lunaris-v1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"A generalist / roleplaying model merge based on Llama 3. Sao10K has carefully selected the values based on extensive personal experimentation and has fine-tuned them to create a customized recipe.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Sao10K/L3-8B-Lunaris-v1/cover_image.d72dfd670089af5cbe1a16a92a538bb4d50201f12892b333b63a7f91f67536e5.webp\", \"tags\": [\"openai\"]", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "026b8ca684efbe3e1e77", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-7B-Instruct-v0.3", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.8, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-7B-Instruct-v0.3\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Mistral-7B-Instruct-v0.3 is an instruction-tuned model, next iteration of of Mistral 7B that has larger vocabulary, newer tokenizer and supports function calling.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.3/cover_image.716d64cdc98717436953bde0b80dede06d7071f66cb46f1df85caaa270e5cdd6.webp\", \"tags\": [\"openai\", \"tools\"], \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.8, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "64f29e13f5d8840cd324", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3.1-70B-Euryale-v2.2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 85.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3.1-70B-Euryale-v2.2\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Euryale 3.1 - 70B v2.2 is a model focused on creative roleplay from Sao10k\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Sao10K/L3.1-70B-Euryale-v2.2/cover_image.f22f2e0fffe03183d6214faed551f62cdaaa3a3c6eefd1bf46b7d3c00b0b4ec4.webp\", \"tags\": [\"json\", \"openai\", \"non-reasoning\", \"structured-output\", \"flex\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 85.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "265c1573c1ff9f292c32", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-opus-4-7", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 500.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-opus-4-7\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Anthropic's most capable production model yet, advancing performance across coding, enterprise workflows, and long-running agentic tasks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-opus-4-7/cover_image.8f8781b46f9e411ae47135b0cf0aa655c509792024b39b2d94385b58d8430c07.webp\", \"tags\": [\"ocr\", \"no-free-anon\", \"multimodal\", \"json\", \"structured-output\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 500.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "d2f9679dcac6f44af435", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-Nemo-Instruct-2407", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.9, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-Nemo-Instruct-2407\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"12B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Mistral-Nemo-Instruct-2407/cover_image.353ef9274d841a75e1f3fcc18cec4bee3df17e8d931b5613492191651d2dd539.webp\", \"tags\": [\"openai\", \"tools\", \"json\", \"non-reasoning\", \"structured", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.9, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "28ab8aef5a1d07ea49cc", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2.5-VL-32B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2.5-VL-32B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"ocr\", \"openai\", \"multimodal\", \"json\", \"non-reasoning\", \"structured-output\", \"cc-native\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 2e-05, \"cents_per_output_token\": 6e-05, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_write\": null, \"rate_per_service_tier_priority\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b261b182cdfbcc6f3aaf", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Reranker-8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Reranker-8B\", \"type\": \"reranker\", \"reported_type\": \"reranker\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B)\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-Reranke", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8da655d12ac7b6195b4f", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2-7B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2-7B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The 7 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen2-7B-Instruct/cover_image.e8c2257ba46edbd20ef17c81343ad40fdf27f7bc3838837d079557accd2879e2.webp\", \"tags\": [\"openai\", \"tools\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2017d9aab82f601c1b3b", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-Small-24B-Instruct-2501", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-Small-24B-Instruct-2501\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed for efficient local deployment. The model achieves 81% accuracy on the MMLU benchmark and performs competitively with larger models like Llam", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b3e4fde08a70fa2a9f6c", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "zai-org/GLM-4.6", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"zai-org/GLM-4.6\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Compared with GLM-4.5, GLM-4.6 brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "d261066260f13e33465a", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Max-Thinking", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 120.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Max-Thinking\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The latest flagship reasoning model in the Qwen3 family. Further enhanced by multiple innovations like adaptive tool-use and advanced test-time scaling techniques\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-Max-Thinking/cover_image.fa7888e2940746f47be3fb3eaa39ecddf187d085e0b96805a24e0db063d46f59.webp\", \"tags\": [\"openai\", \"tools\", \"no-free-anon\", \"json\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 120.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3add2dc84be4edde906e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "openchat/openchat-3.6-8b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"openchat/openchat-3.6-8b\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Openchat 3.6 is a LLama-3-8b fine tune that outperforms it on multiple benchmarks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/openchat/openchat-3.6-8b/cover_image.c5792073e4034a0847ff5112e00356adb411c4a5c900ed22c32ad65c5d97e8d1.webp\", \"tags\": [\"openai\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 5.5e-06, \"c", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8879c37271f88c871245", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "PaddlePaddle/PaddleOCR-VL-0.9B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 14.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"PaddlePaddle/PaddleOCR-VL-0.9B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languag", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 14.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8a0a6071bcb111786546", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-ASR-1.7B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 750.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-ASR-1.7B\", \"type\": \"automatic-speech-recognition\", \"reported_type\": \"automatic-speech-recognition\", \"description\": \"Qwen3-ASR-1.7B is the flagship model of the Qwen3-ASR family: multilingual language identification and speech recognition across 30 languages and 22 Chinese dialects, built on Qwen3-Omni. It reaches state-of-the-art accuracy among open-source ASR models (competitive with strong commercial APIs), with unified streaming/offline inference and segment- and wo", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 750.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "059a92a1cf6e65426cca", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Audio8/Audio8-TTS-Preview-0.6b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 500.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Audio8/Audio8-TTS-Preview-0.6b\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"A 0.6B-parameter multilingual text-to-speech model with zero-shot voice cloning, supporting 11 languages.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Audio8/Audio8-TTS-Preview-0.6b/cover_image.a1482bb329189b982949fb8bd81c8e293ee4b42abaa353ac0bce89bbf751c507.webp\", \"tags\": [\"voice\", \"openai\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"inp", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 500.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "55e053fc030da908ee27", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "NousResearch/Hermes-3-Llama-3.1-405B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 100.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"NousResearch/Hermes-3-Llama-3.1-405B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Hermes 3 is a cutting-edge language model that offers advanced capabilities in roleplaying, reasoning, and conversation. It's a fine-tuned version of the Llama-3.1 405B foundation model, designed to align with user needs and provide powerful control. Key features include reliable function calling, structured output, generalist assistant capabilities, and improved ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 100.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "138ed72e09050db6fe02", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-4-31B-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 13.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-4-31B-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemma-4-31B-it/cover_image.0b8bfa626859a2b86c0f60c5bcb5847521cbd34a013b8f485b59e80f3a100836.webp\", \"tags\": [\"multimodal\", \"openai\", \"tools\", \"cc-native\", \"structured-outp", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 13.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2ed3e1256188fac0870c", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-2-27b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-2-27b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma is a family of lightweight, state-of-the-art open models from Google. Gemma-2-27B delivers the best performance for its size class, and even offers competitive alternatives to models more than twice its size. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemma-2-27b-it/cover_image.7278882b03ca6732cf6374aaab42734a2ede6343b1b89421f15ad0fc27e3936c.webp\", \"ta", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "37fec4c2e711d17577e7", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V4-Pro", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 130.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V4-Pro\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek V4 Pro is an MoE model with 1.6T total parameters (49B active) and a 1M-token context window. It's built for advanced reasoning, coding, and long-running agent tasks, and performs well on knowledge, math, and software engineering benchmarks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-V4-Pro/cover_image.2aafc71db68ab31f66b467460c86", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 130.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "406dba9f08dfd3788fca", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "microsoft/Phi-4-multimodal-instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"microsoft/Phi-4-multimodal-instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K token context length. The model underwent an enhancement process, incorporating both supervi", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "500dd66ea23507e11098", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-VL-4B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 10.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-VL-4B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\", \"cover_img_url\": \"https:", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 10.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "751f570760ea6bea48b6", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-7B-Instruct-v0.2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-7B-Instruct-v0.2\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.2 generative text model using a variety of publicly available conversation datasets.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.2/cover_image.429fef8a2a09e5c4104ede511db12beaea9d3917c4754d709b05a65d5d6f6c1f.webp\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f1447b8a7a81ba08d5c1", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K2.7-Code", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 68.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K2.7-Code\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.\", \"cover_img_url\": \"https://shared.de", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 68.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "97f1d29e860c96a8fe46", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Embedding-0.6B-batch", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 0.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Embedding-0.6B-batch\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7b9334678c6f37803e84", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Meta-Llama-3.1-405B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 80.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Meta-Llama-3.1-405B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3.1-405B-Instruct/cover_image.3613f6cc9339458731dfdff96dbf39481e1857ffc29d112eb5ef5426556f93e1.webp\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 80.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "93895a6e87e0c82c17d4", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-3.3-70B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 23.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-3.3-70B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama 3.3-70B is a multilingual LLM trained on a massive dataset of 15 trillion tokens, fine-tuned for instruction-following and conversational dialogue. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It achieves state-of-the-art performance on ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 23.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "fc2285589e908576d4be", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-4-E4B-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-4-E4B-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"cc-native\", \"can-disable-reasoning\", \"openai\", \"priority\", \"tools\", \"reasoning\", \"flex\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 2e-06, \"cents_per_output_token\": 1e-05, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_write\": null, \"rate_per_service_tier_priority\": 1.5, ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c80031bb83247308bd54", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "stepfun-ai/Step-3.7-Flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"stepfun-ai/Step-3.7-Flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Step 3.7 Flash is an open-source multimodal reasoning model by StepFun with 198B total parameters (11B active) using Mixture of Experts. It accepts text and image inputs and features a 256K context window, selectable reasoning effort, tool calling, and agentic capabilities for coding and search workflows, scoring 80.9% on GPQA Diamond and 56.3% on SWE-bench Pro.\", \"cover_img", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0bfc3ae6a5a745dc8ee1", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K2-Instruct-0905", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K2-Instruct-0905\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and bet", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "adacd070a5a024e3bd68", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Meta-Llama-3.1-70B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3.1-70B-Instruct/cover_image.9a5d4e05f46ed0cf09ef22a6771aa701bd3ffaadfcd68fa7ca272bc8c1c7b8e6.webp\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "6c7e2091c7536a36830e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V3-0324", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 24.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V3-0324\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-V3-0324/cover_image.2132971065034c302886aaa95cfd9661a96989fbe12ec2d93e78ac4c831bf66d.webp\", \"tags\": [\"openai\", \"tools\", \"b200\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 24.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "4d5d461af1f07d799526", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "nvidia/Llama-3.3-Nemotron-Super-49B-v1.5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Llama-3.3-Nemotron-Super-49B-v1.5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama-3.3-Nemotron-Super-49B-v1.5 is a large language model (LLM) optimized for advanced reasoning, conversational interactions, retrieval-augmented generation (RAG), and tool-calling tasks. Derived from Meta's Llama-3.3-70B-Instruct, it employs a Neural Architecture Search (NAS) approach, significantly enhancing efficiency and reducing memory requirements. \",", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b8fc191fb2ce61a31fc9", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "inworld-ai/realtime-tts-1.5-mini", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2500.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"inworld-ai/realtime-tts-1.5-mini\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"Fast multilingual text-to-speech model by Inworld AI with 130+ preset voices across 15 languages. Supports voice cloning, word-level timestamps, and streaming. Optimized for low-latency applications with <130ms time-to-first-audio.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/inworld-ai/realtime-tts-1.5-mini/cover_image.bc7fa4a01efac7cb31b6e68ea482f3f3f18ae2d", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2500.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "6468f753f32c85e1cf37", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-R1-Distill-Qwen-32B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek R1 Distill Qwen 32B is a distilled large language model based on Qwen 2.5 32B, using outputs from DeepSeek R1. It outperforms OpenAI's o1-mini across various benchmarks, achieving new state-of-the-art results for dense models. Other benchmark results include: AIME 2024: 72.6 | MATH-500: 94.3 | CodeForces Rating: 1691.\", \"cover_img_url\": \"https://share", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "38500170833a2285c556", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "Phind/Phind-CodeLlama-34B-v2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 60.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Phind/Phind-CodeLlama-34B-v2\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Phind-CodeLlama-34B-v2 is an open-source language model that has been fine-tuned on 1.5B tokens of high-quality programming-related data and achieved a pass@1 rate of 73.8% on HumanEval. It is multi-lingual and proficient in Python, C/C++, TypeScript, Java, and more. It has been trained on a proprietary dataset of instruction-answer pairs instead of code completion exampl", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 60.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5ff4c826fb9496f94f88", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-3-7-sonnet-latest", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 330.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-3-7-sonnet-latest\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"ocr\", \"openai\", \"tools\", \"multimodal\", \"no-free-anon\", \"json\", \"non-reasoning\", \"structured-output\", \"cc-native\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 0.00033, \"cents_per_output_token\": 0.00165, \"rate_per_input_token_cached\": 0.1, \"rate_per_input_token_cache_write\": null", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 330.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1aacde4095c820ee3578", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-R1-0528", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-R1-0528\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-R1-0528/cover_image.1c2b6d82000fef8e12c4318b3f5b5d71411fc73bcf000ff2674b32e6af8dba75.webp\", \"tags\": [\"openai\", \"tools\", \"reasoning\", \"b200\", \"json\", \"non-reasoning\", \"structured-output\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ee7a27ccb0b8ade53a5f", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2-72B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 35.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2-72B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The 72 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen2-72B-Instruct/cover_image.6771b7ff122c6ffaa9d5ae6b6ab54db0d46079a8f90441fa7770d60cfd4c6f4f.webp\", \"tags\": [\"openai\", \"tools\"], \"pricing\": {\"short\": null, \"full\": null, \"table\": null, \"t", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-14T13:05:15+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 35.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." } ] }