List all models and their properties | OpenRouter

curl https://openrouter.ai/api/v1/models \
     -H "Authorization: Bearer <token>"

{
  "data": [
    {
      "architecture": {
        "input_modalities": [
          "text"
        ],
        "modality": "text->text",
        "output_modalities": [
          "text"
        ],
        "instruct_type": "chatml",
        "tokenizer": "GPT"
      },
      "canonical_slug": "openai/gpt-4",
      "context_length": 8192,
      "created": 1692901234,
      "default_parameters": null,
      "id": "openai/gpt-4",
      "links": {
        "details": "/api/v1/models/openai/gpt-5.4/endpoints"
      },
      "name": "GPT-4",
      "per_request_limits": null,
      "pricing": {
        "completion": "0.00006",
        "prompt": "0.00003",
        "image": "0",
        "request": "0"
      },
      "supported_parameters": [
        "temperature",
        "top_p",
        "max_tokens"
      ],
      "supported_voices": null,
      "top_provider": {
        "is_moderated": true,
        "context_length": 8192,
        "max_completion_tokens": 4096
      },
      "description": "GPT-4 is a large multimodal model that can solve difficult problems with greater accuracy.",
      "expiration_date": null,
      "knowledge_cutoff": null
    }
  ]
}

Authentication

AuthorizationBearer

API key as bearer token in Authorization header

Query parameters

categoryenumOptional

Filter models by use case category

supported_parametersstringOptional

Filter models by supported parameter (comma-separated)

output_modalitiesstringOptional

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”.

sortenumOptional

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). When omitted, the existing default ordering is preserved.

use_rssstringOptional

Return results as RSS feed

use_rss_chat_linksstringOptional

Use chat links in RSS feed items

Response

Returns a list of models or RSS feed

datalist of objects

List of available models

Errors

400

Bad Request Error

500

Internal Server Error