Skip to main content

Quickstart

Get up and running with the Model Graph API in under a minute. All read endpoints are public — no API key or authentication required.

Base URL​

https://api.modelgraph.ai/api/v1

1. List All Providers​

Start by seeing which AI model providers are tracked:

curl https://api.modelgraph.ai/api/v1/providers
{
  "providers": [
    {
      "slug": "anthropic",
      "name": "Anthropic",
      "website_url": "https://anthropic.com",
      "family_count": 4,
      "model_count": 18
    },
    {
      "slug": "openai",
      "name": "OpenAI",
      "website_url": "https://openai.com",
      "family_count": 6,
      "model_count": 32
    }
  ]
}

2. Explore a Model Family​

See how a model family has evolved over time:

curl https://api.modelgraph.ai/api/v1/families/claude-sonnet
{
  "slug": "claude-sonnet",
  "name": "Claude Sonnet",
  "provider": {
    "slug": "anthropic",
    "name": "Anthropic"
  },
  "description": "Claude Sonnet series — balanced speed and intelligence",
  "is_open_source": false,
  "models": [
    {
      "slug": "claude-3-sonnet-20240229",
      "display_name": "Claude 3 Sonnet",
      "status": "deprecated",
      "release_date": "2024-02-29"
    },
    {
      "slug": "claude-3-5-sonnet-20241022",
      "display_name": "Claude 3.5 Sonnet",
      "status": "active",
      "release_date": "2024-10-22"
    },
    {
      "slug": "claude-sonnet-4-6",
      "display_name": "Claude Sonnet 4.6",
      "status": "latest",
      "release_date": "2025-10-15"
    }
  ]
}

3. Resolve a Model String​

The most powerful endpoint. Given any model identifier string found in code, resolve it to a known model and get the recommended upgrade:

curl "https://api.modelgraph.ai/api/v1/resolve?q=anthropic.claude-3-5-sonnet-20241022-v2:0"
{
  "matched_model": {
    "slug": "claude-3-5-sonnet-20241022",
    "display_name": "Claude 3.5 Sonnet",
    "status": "active",
    "family": "claude-sonnet"
  },
  "matched_alias": {
    "alias": "anthropic.claude-3-5-sonnet-20241022-v2:0",
    "source": "bedrock"
  },
  "confidence": 1.0,
  "is_latest": false,
  "upgrade": {
    "slug": "claude-sonnet-4-6",
    "display_name": "Claude Sonnet 4.6",
    "status": "latest"
  },
  "upgrade_alias": {
    "alias": "anthropic.claude-sonnet-4-6-v1:0",
    "source": "bedrock"
  }
}

Notice how the upgrade_alias returns a Bedrock-format string because the input was a Bedrock-format alias. This is format-preserving replacement — you can drop the upgrade string directly into your code without any format conversion.

4. Search for Models​

Find models by name, slug, or keyword:

curl "https://api.modelgraph.ai/api/v1/search?q=llama%2070b"
{
  "results": [
    {
      "slug": "llama-3.3-70b-instruct",
      "display_name": "Llama 3.3 70B Instruct",
      "family": "llama-3",
      "provider": "meta",
      "score": 0.95
    },
    {
      "slug": "llama-3.1-70b-instruct",
      "display_name": "Llama 3.1 70B Instruct",
      "family": "llama-3",
      "provider": "meta",
      "score": 0.91
    }
  ]
}

Rate Limits​

Public endpoints are rate-limited to 100 requests per minute per IP address. Rate limit headers are included in every response:

HeaderDescription
X-RateLimit-LimitMaximum requests per minute
X-RateLimit-RemainingRequests remaining in the current window
X-RateLimit-ResetUnix timestamp when the window resets

Next Steps​