{
  "id": "gpt-4o-mini",
  "identity": {
    "family": "gpt-4o",
    "display_name": "GPT-4o mini",
    "hub_id": null,
    "api_name": "gpt-4o-mini",
    "revision": null,
    "variants": [],
    "license": "OpenAI API terms of use",
    "commercial_use": true,
    "commercial_use_note": "Paid OpenAI API under OpenAI's terms; tenants can bring their own key.",
    "release_date": "2024-07",
    "paper_url": null,
    "repo_url": null
  },
  "task": {
    "category": "generation",
    "modalities_in": [
      "text",
      "image"
    ],
    "modalities_out": [
      "text",
      "structured"
    ],
    "best_at": "Cheap short generations such as query expansion (query_expand's default expansion_model) and the fallback chat model of the universal inference endpoint.",
    "worst_at": "Video and audio input (needs another model); the stage's 3 s query_expand budget leaves little room for slow provider responses."
  },
  "io": {
    "input": {
      "text": "chat messages",
      "image": "image URLs (universal__api converts base64 media to data URIs)"
    },
    "output": {
      "text": "chat completion"
    }
  },
  "mixpeek_wiring": {
    "extractors": [],
    "feature_uris": [],
    "vector_indexes": [],
    "retriever_stages": [
      "query_expand",
      "llm_enrich"
    ],
    "composes_with": [
      "query_expand (gpt-4o-mini) -> several feature_search calls fused",
      "llm_enrich with legacy inference_name openai:gpt-4o-mini resolves to universal/api with model gpt-4o-mini"
    ]
  },
  "run": {
    "status": "api",
    "status_reason": "Provider API. universal__api uses it when a request names no model (params.get('model', 'gpt-4o-mini')); query_expand calls it through CentralLLMService.",
    "serve_apps": [
      "universal__api"
    ],
    "runtime": "OpenAI chat completions (shared.models.llm OpenAIProvider; universal__api _handle_chat)",
    "weights_format": "api",
    "trust_remote_code": false,
    "size_on_disk_mb": null,
    "params_millions": null,
    "preprocessing": "Stage prompt templates ({{QUERY}}, {{NUM_EXPANSIONS}} for query_expand).",
    "postprocessing": "Text, parsed into expansions or enrichment fields.",
    "serving_shape": "realtime",
    "batch_size": null,
    "serve_batch": null,
    "scale_to_zero": {
      "min_replicas": 0,
      "max_replicas": 6,
      "idle_timeout_s": 600,
      "memory_gb": null,
      "num_cpus": 0.1,
      "num_gpus": 0,
      "cold_start_s": {
        "warm_node_s": null,
        "new_node_s": null,
        "source": null
      },
      "cpu_fallback": true
    }
  },
  "cost": {
    "unmeasured": true,
    "measured": null,
    "note": "Billed per token by OpenAI; no committed measurement."
  },
  "evidence": {
    "unmeasured": true,
    "items": []
  },
  "refs": [
    "api://openai/gpt-4o-mini"
  ],
  "formats": [
    {
      "ref": "api://openai/gpt-4o-mini",
      "format": "api",
      "file": null,
      "loader": "provider SDK, called by model name",
      "supported_today": true
    }
  ],
  "use_cases": [
    "tagging",
    "captioning"
  ],
  "recommended": {
    "value": false,
    "for": [],
    "reason": null
  },
  "demos": [],
  "seo": {
    "title": "GPT-4o mini: language model",
    "description": "GPT-4o mini is a text and image language model (OpenAI API terms of use). Called on Mixpeek through the provider API.",
    "keywords": [
      "GPT-4o mini",
      "gpt-4o",
      "language",
      "gpt-4o-mini",
      "tagging",
      "captioning"
    ],
    "faqs": [
      {
        "q": "What is GPT-4o mini best at?",
        "a": "Cheap short generations such as query expansion (query_expand's default expansion_model) and the fallback chat model of the universal inference endpoint."
      },
      {
        "q": "What are the limits of GPT-4o mini?",
        "a": "Video and audio input (needs another model); the stage's 3 s query_expand budget leaves little room for slow provider responses."
      },
      {
        "q": "Can GPT-4o mini be used commercially?",
        "a": "Yes. Paid OpenAI API under OpenAI's terms; tenants can bring their own key."
      },
      {
        "q": "How does GPT-4o mini run on Mixpeek?",
        "a": "Provider API. universal__api uses it when a request names no model (params.get('model', 'gpt-4o-mini')); query_expand calls it through CentralLLMService."
      }
    ]
  },
  "last_verified": "2026-11-05",
  "sources": [
    "https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence/",
    "server/engine/inference/llm/routes.py",
    "server/shared/retrievers/stages/filter/query_expand/models.py",
    "server/shared/retrievers/inference/resolver.py",
    "server/shared/retrievers/stages/enrich/llm/models.py"
  ],
  "registry": {
    "universal__api": {
      "deployment": "universal__api",
      "service_id": "universal/api",
      "routes": "engine/inference/llm/routes.py",
      "route_prefix": "/universal/api",
      "enabled": true,
      "description": "Universal inference endpoint routing to multiple providers and modalities. Supports: OpenAI (GPT, embeddings, Whisper), Google (Gemini, Vertex embeddings), Anthropic (Claude). Routes based on model parameter.",
      "capabilities": {
        "category": "generation",
        "modality_input": [
          "text"
        ],
        "modality_output": "text",
        "supports_batch": true,
        "reranking_mode": null
      },
      "vector_config": null,
      "serve": {
        "min_replicas": 0,
        "max_replicas": 6,
        "idle_timeout_s": 600,
        "target_ongoing_requests": 25,
        "num_cpus": 0.1,
        "num_gpus": 0,
        "memory_gb": null,
        "pinnable": false,
        "placement": "worker",
        "enabled": true
      },
      "interactive_twin": false,
      "interactive_serve": null,
      "schemas": {
        "input": null,
        "output": null,
        "config": null
      }
    }
  },
  "templates": [],
  "usage": {
    "namespaces": null,
    "collections": null,
    "uncounted": true,
    "templates": 0,
    "counted_at": null,
    "source": null
  },
  "facets": {
    "status": "api",
    "category": "generation",
    "family": "gpt-4o",
    "license": "OpenAI API terms of use",
    "commercial_use": true,
    "modalities_in": [
      "text",
      "image"
    ],
    "modalities_out": [
      "text",
      "structured"
    ],
    "use_cases": [
      "tagging",
      "captioning"
    ],
    "recommended": false,
    "release_date": "2024-07",
    "params_millions": null,
    "size_on_disk_mb": null,
    "vector_dims": null,
    "vector_distance": null,
    "weights_format": "api",
    "formats": [
      "api"
    ],
    "loadable_today": true,
    "trust_remote_code": false,
    "cpu_fallback": true,
    "num_gpus": 0,
    "memory_gb": null,
    "min_replicas": 0,
    "serving_shape": "realtime",
    "served": true,
    "ref_schemes": [
      "api"
    ],
    "has_evidence": false,
    "cost_measured": false,
    "template_count": 0,
    "usage_namespaces": null,
    "usage_collections": null,
    "usage_uncounted": true,
    "has_demo": false,
    "rank_score": 2
  },
  "rank_score": 2
}