OpenRouter Models API

Base URL

https://openrouter.ai/api/v1

Authentication

No API key to list models. Actually calling a model for inference requires an API key and credit.

Rate limit

No published limit on the catalogue endpoint. It changes a few times a day at most.

Pricing

Free to read. Inference through OpenRouter is paid per token.

CORS

Enabled — callable directly from browser JavaScript

Official docs

Read the docs

Every request below was executed against the live API on 2026-08-21, and the response shown is the real body it returned — not an illustration.

curl 'https://openrouter.ai/api/v1/models'

const res = await fetch("https://openrouter.ai/api/v1/models");
if (!res.ok) throw new Error(`Request failed: ${res.status}`);
const data = await res.json();
console.log(data);

import requests

res = requests.get("https://openrouter.ai/api/v1/models", timeout=20)
res.raise_for_status()
print(res.json())

{
  "data": [
    {
      "id": "stealth/ox-alpha",
      "canonical_slug": "stealth/ox-alpha",
      "hugging_face_id": null,
      "name": "Ox Alpha",
      "created": 1787256295,
      "description": "Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, complex reasoning, and workflows that combine text with...",
      "context_length": 1048576,
      "architecture": {
        "modality": "text+image+video->text",
        "input_modalities": [
          "text",
          "image",
          "video"
        ],
        "output_modalities": [
          "text"
        ],
        "tokenizer": "Other",
        "instruct_type": null
      },
      "pricing": {
        "prompt": "0",
        "completion": "0"
      },
      "top_provider": {
        "context_length": 1048576,
        "max_completion_tokens": 131072,
        "is_moderated": false
      },
      "per_request_limits": null,
      "supported_parameters": [
        "include_reasoning",
        "max_tokens",
        "reasoning",
        "reasoning_effort",
        "response_format",
        "temperature",
        "tool_choice",
        "tools",
        "top_k",
        "top_p"
      ],
      "default_parameters": {
        "temperature": 1,
        "top_p": 0.95
      },
      "supported_voices": null,
      "knowledge_cutoff": null,
      "expiration_date": "2098-12-31",
      "links": {
        "details": "/api/v1/models/stealth/ox-alpha/endpoints"
      },
      "reasoning": {
        "mandatory": true,
        "defau

dataarray

Every model in the catalogue.

data[].id / canonical_slugstring

Model identifier in `author/model` form — this is what you pass when making an inference request.

data[].namestring

Human-readable display name.

data[].descriptionstring

Provider-supplied summary of what the model is for.

data[].context_lengthinteger

Maximum context window in tokens.

data[].pricingobject

USD per token as strings, with `prompt` and `completion` at minimum and often image, request and reasoning rates too. Multiply by a million for the usual per-MTok figure.

data[].architecture.modalitystring

Compact summary such as `text+image+video->text`.

data[].architecture.input_modalities / output_modalitiesarray

Precise lists of what the model accepts and produces.

data[].architecture.tokenizerstring

Tokenizer family, which matters if you are counting tokens yourself.

data[].top_providerobject

The default upstream provider's context limit and whether it moderates requests.

data[].supported_parametersarray

Request options this model honours — tool calling, structured outputs, reasoning effort and so on.

data[].hugging_face_idstring

Corresponding Hugging Face repository for open-weight models; null for proprietary ones.

data[].createdinteger

Unix timestamp of when the model was added to the catalogue.

• Build a model picker showing live pricing and context limits
• Compare per-token costs across providers before choosing a model
• Check whether a model supports tool calling before wiring it up
• Track when new models appear in the catalogue