Free Models API

Found an issue?

Report it on GitHub

Get Started

Start using free LLM models in your app in 3 steps.

1

What are you building?

Filter models by capability to find the best fit for your use case.

0 free models

2

What matters most?

Order results by your priority.

3

Ready to code?

Copy the snippet and start building.

Filter:
Sort:
https://free-models-api.pages.dev/api/v1/models/openrouter?sort=contextLength
1

Get an OpenRouter API Key

OpenRouter provides a unified API for accessing many LLM providers. Sign up for free and create an API key.

2

Fetch Free Models

After setting up OpenRouter, add this to fetch available free models.

const res = await fetch('https://free-models-api.pages.dev/api/v1/models/openrouter?sort=contextLength');
const { models } = await res.json();

// Pass to OpenRouter - it auto-fallbacks through the list
const modelIds = models.map(m => m.id);
3

Pass Model IDs

Replace your model config with the fetched IDs. OpenRouter auto-fallbacks through the list.

models: modelIds

Free Models

Select filters to find models that match your needs. Copy the generated code snippet to use in your app.

Filter:
Sort by

0 free models

Loading...

API Reference

GET /api/v1/models/openrouter
Returns the list of currently available free models.

Query Parameters

ParameterTypeDescription
filterstringComma-separated: chat, vision, coding, longContext, reasoning
sortstringOne of: contextLength, maxOutput, name, provider, capable

Response

{
  "models": [
    {
      "id": "google/gemini-2.0-flash-exp:free",
      "name": "Gemini 2.0 Flash",
      "contextLength": 1000000,
      "maxCompletionTokens": 8192,
      "description": "...",
      "modality": "text->text",
      "inputModalities": ["text", "image"],
      "outputModalities": ["text"],
      "supportedParameters": ["tools", "reasoning"],
      "isModerated": false
    }
  ],
  "feedbackCounts": {
    "model-id": { "rateLimited": 0, "unavailable": 0, "error": 0 }
  },
  "lastUpdated": "2024-12-29T10:00:00Z",
  "filters": ["vision"],
  "sort": "contextLength",
  "count": 15
}

Caching: 15-minute stale threshold. Cache-Control: public, s-maxage=900

POST /api/feedback
Report issues with a model (rate limiting, errors, unavailability).

Request Body

FieldTypeRequiredDescription
modelIdstringYesThe model ID to report
issuestringYesOne of: rate_limited, unavailable, error
detailsstringNoOptional description of the issue
sourcestringNoYour app identifier (default: "anonymous")

Request Example

{
  "modelId": "google/gemini-2.0-flash-exp:free",
  "issue": "rate_limited",
  "details": "Getting 429 after ~10 requests",
  "source": "my-app"
}

Response

{ "received": true }

Errors

  • 400 - Missing modelId or invalid issue type
  • 500 - Server error

Code Examples

Basic Fetch
Fetch the list of free models and log the count.
const response = await fetch('https://free-models-api.pages.dev/api/v1/models/openrouter');
const { models, count } = await response.json();
console.log(`Found ${count} free models`);
With Filters
Filter models by capability and sort order.
// Get only vision-capable models, sorted by context length
const url = 'https://free-models-api.pages.dev/api/v1/models/openrouter?filter=vision&sort=contextLength';
const { models } = await fetch(url).then(r => r.json());
Full Integration with OpenRouter
Complete example with model fallback for reliable responses.
import { OpenRouter } from '@openrouter/sdk';

async function chat(message: string) {
  // 1. Get current free models
  const { models } = await fetch(
    'https://free-models-api.pages.dev/api/v1/models/openrouter?sort=capable'
  ).then(r => r.json());

  // 2. Create OpenRouter client
  const openRouter = new OpenRouter({
    apiKey: process.env.OPENROUTER_API_KEY,
  });

  // 3. Send message with automatic fallback
  const completion = await openRouter.chat.send({
    models: models.map(m => m.id),
    messages: [{ role: 'user', content: message }],
  });

  return completion.choices[0].message.content;
}
Report an Issue
Help improve model availability data by reporting issues.
await fetch('https://free-models-api.pages.dev/api/feedback', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    modelId: 'google/gemini-2.0-flash-exp:free',
    issue: 'rate_limited',
    details: 'Getting 429 after ~10 requests',
    source: 'my-app',
  }),
});