How to use the API

The full catalog is available as static JSON, CORS-enabled, served from the edge. You can also install the npm package or point your AI agent at /llms.txt.

Building with an AI agent? Point it at /llms.txt for a machine-readable overview, or copy any snippet below.

Full catalog

Returns every model in the catalog with all parameters, types, defaults, and ranges.

GET

curl https://modelparams.dev/api/v1/models.json

Each entry is keyed by provider/model for API-key variants. Subscription variants append -subscription.

Single model

Fetch the full definition for a specific model, including its provider.

GET

curl https://modelparams.dev/api/v1/models/anthropic/claude-opus-4-7.json

Parameters only

If you only need the parameters for a model without knowing the provider, use the providerless endpoint.

GET

curl https://modelparams.dev/api/v1/models/openai/gpt-5.5.json

Validate a request

POST a model and the parameters you intend to send. The response reports unknown parameters, values outside their range, and combinations the provider rejects — plus a corrected payload you can send as-is.

POST

curl -s https://modelparams.dev/api/v1/validate \
  -H 'Content-Type: application/json' \
  -d '{"model":"anthropic/claude-3-opus-20240229","params":{"temperature":0.5,"top_p":0.9}}'

{
  "model": "anthropic/claude-3-opus-20240229",
  "valid": false,
  "issues": [
    {
      "path": "top_p",
      "code": "not_applicable",
      "message": "top_p does not apply when temperature ≠ 1",
      "conflictsWith": ["temperature"]
    }
  ],
  "safeParams": { "temperature": 0.5 }
}

Every issue carries a code: unknown_parameter, invalid_value, or not_applicable for a conflict with another value in the same request.

MCP server

Want your coding agent to check the catalog itself? The MCP server has its own page: /mcp-server — install commands, the four tools, and their schemas.

JSON Schema

Every entry validates against a JSON Schema you can use in your editor or CI pipeline.

GET

curl https://modelparams.dev/api/v1/schema.json

Add this header to any YAML you author for autocomplete in VS Code:

# yaml-language-server: $schema=https://modelparams.dev/api/v1/schema.json

npm package

Install the package to query the catalog locally or in your build pipeline.

npm i modelparams

Logos

Provider logos are available as SVGs. They use currentColor so they inherit your text color.

curl https://modelparams.dev/assets/logos/anthropic.svg

Replace anthropic with any provider slug: openai, google, meta, mistral, deepseek, etc.

Contribute

The data lives in YAML under models/{provider}/{model}-{auth}.yaml in the GitHub repo. Open a PR, CI validates against the schema and rebuilds the site automatically.