e94bbd33847b

OpenAPI 3.1.0MITraw.githubusercontent.com2026-08-14977651.3 MB

Models

List all models and their properties

get/models

Query parameters

offsetinteger nullable

Number of records to skip for pagination. When both offset and limit are omitted, the full list is returned

limitinteger

Maximum number of records to return (max 1000). When both offset and limit are omitted, the full list is returned

Example:500

Maximum number of records to return (max 1000). When both offset and limit are omitted, the full list is returned

Filter models by use case category

Example:programming

Filter models by use case category

supported_parametersstring

Filter models by supported parameter (comma-separated)

Example:temperature

Filter models by supported parameter (comma-separated)

output_modalitiesstring

Filter models by output modality. Accepts a comma-separated list of modalities (text, image, audio, embeddings) or "all" to include all models. Defaults to "text".

Example:text

Filter models by output modality. Accepts a comma-separated list of modalities (text, image, audio, embeddings) or "all" to include all models. Defaults to "text".

Sort the returned models server-side. Prefer this over fetching the full list and sorting client-side. Options: pricing-low-to-high, pricing-high-to-low (average prompt/completion price), context-high-to-low (context length), throughput-high-to-low, latency-low-to-high (recent median performance), most-popular, top-weekly (tokens processed in the last week), newest (creation date), intelligence-high-to-low, coding-high-to-low, agentic-high-to-low (Artificial Analysis indices), design-arena-elo-high-to-low (best Design Arena ELO across arenas). Models without a score for the chosen benchmark are placed last. When omitted, the existing default ordering is preserved.

Example:newest

use_rssstring

Return results as RSS feed

Example:true

Return results as RSS feed

use_rss_chat_linksstring

Use chat links in RSS feed items

Example:true

Use chat links in RSS feed items

qstring

Free-text search by model name or slug.

Example:gpt-4

Free-text search by model name or slug.

input_modalitiesstring

Filter models by input modality. Comma-separated list of: text, image, audio, file.

Example:text,image

Filter models by input modality. Comma-separated list of: text, image, audio, file.

contextinteger

Minimum context length (tokens). Models with smaller context are excluded.

Example:128000

Minimum context length (tokens). Models with smaller context are excluded.

min_pricenumber nullable

Minimum prompt price in $/M tokens.

max_pricenumber nullable

Maximum prompt price in $/M tokens.

Example:10

Maximum prompt price in $/M tokens.

archstring

Filter models by architecture/model family (e.g. GPT, Claude, Gemini, Llama).

Example:GPT

Filter models by architecture/model family (e.g. GPT, Claude, Gemini, Llama).

model_authorsstring

Filter models by the organization that created the model. Comma-separated list of author slugs.

Example:openai,anthropic

Filter models by the organization that created the model. Comma-separated list of author slugs.

providersstring

Filter models by hosting provider. Comma-separated list of provider names.

Example:OpenAI,Anthropic

Filter models by hosting provider. Comma-separated list of provider names.

distillable'true' | 'false'

Filter by distillation capability. "true" returns only distillable models, "false" excludes them.

Example:true

Filter by distillation capability. "true" returns only distillable models, "false" excludes them.

zdr'true'

When set to "true", return only models with zero data retention endpoints.

Example:true

When set to "true", return only models with zero data retention endpoints.

region'eu' | 'us'

Filter to models with endpoints in the given data region ("eu" or "us").

Example:eu

Filter to models with endpoints in the given data region ("eu" or "us").

min_output_pricenumber nullable

Minimum completion (output) price in $/M tokens.

max_output_pricenumber nullable

Maximum completion (output) price in $/M tokens.

Example:10

Maximum completion (output) price in $/M tokens.

min_age_daysinteger nullable

Minimum model age in days since its creation date.

max_age_daysinteger nullable

Maximum model age in days since its creation date.

Example:90

Maximum model age in days since its creation date.

min_intelligence_indexnumber nullable

Minimum Artificial Analysis intelligence index.

Example:50

Minimum Artificial Analysis intelligence index.

max_intelligence_indexnumber nullable

Maximum Artificial Analysis intelligence index.

Example:100

Maximum Artificial Analysis intelligence index.

min_coding_indexnumber nullable

Minimum Artificial Analysis coding index.

Example:50

Minimum Artificial Analysis coding index.

max_coding_indexnumber nullable

Maximum Artificial Analysis coding index.

Example:100

Maximum Artificial Analysis coding index.

min_agentic_indexnumber nullable

Minimum Artificial Analysis agentic index.

Example:50

Minimum Artificial Analysis agentic index.

max_agentic_indexnumber nullable

Maximum Artificial Analysis agentic index.

Example:100

Maximum Artificial Analysis agentic index.

min_tool_success_ratenumber nullable

Minimum tool-calling success rate, as a fraction in [0, 1] (e.g. 0.9 = 90% of requests finishing with a tool_calls finish reason).

Example:0.9

Minimum tool-calling success rate, as a fraction in [0, 1] (e.g. 0.9 = 90% of requests finishing with a tool_calls finish reason).

max_tool_success_ratenumber nullable

Maximum tool-calling success rate, as a fraction in [0, 1].

Example:1

Maximum tool-calling success rate, as a fraction in [0, 1].

Response

Returns a list of models or RSS feed

dataModel[] required— unresolved $ref

List of available models

total_countinteger required

Total number of models matching the query

Example response

{
  "data": [
    {
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "instruct_type": "chatml",
        "modality": "text->text",
        "output_modalities": [
          "text"
        ],
        "tokenizer": "GPT"
      },
      "canonical_slug": "openai/gpt-4",
      "context_length": 8192,
      "created": 1692901234,
      "default_parameters": null,
      "description": "GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.",
      "expiration_date": null,
      "id": "openai/gpt-4",
      "knowledge_cutoff": null,
      "links": {
        "details": "/api/v1/models/openai/gpt-4/endpoints"
      },
      "name": "GPT-4",
      "per_request_limits": null,
      "pricing": {
        "completion": "0.00006",
        "image": "0",
        "prompt": "0.00003",
        "request": "0"
      },
      "supported_parameters": [
        "temperature",
        "top_p",
        "max_tokens",
        "frequency_penalty",
        "presence_penalty"
      ],
      "supported_voices": null,
      "top_provider": {
        "context_length": 8192,
        "is_moderated": true,
        "max_completion_tokens": 4096
      }
    }
  ],
  "links": {
    "next": "/api/v1/models?offset=500&limit=500"
  },
  "total_count": 150
}