Developers & agents

Open data, open door.

Everything the radar measures is available as JSON, and as tools an AI assistant can call directly. Read-only, no keys, CORS-open. Every response carries its own provenance — whether a number was measured or is a fixture, and when it was collected — so what you build on it can be as honest as the site.

Quick start

Top of the board, with the signals behind each Heat Score:

curl https://aimodelradar.dev/api/v1/models?limit=5

Which tracked models fit an RTX 4090 at 16K context:

curl "https://aimodelradar.dev/api/v1/fit?hardware=rtx-4090&context=16384"

Current GPU rental medians:

curl https://aimodelradar.dev/api/v1/prices

Endpoints

Path	Returns	Parameters
GET /api/v1/models	Tracked models ranked by Heat Score: score, confidence, direction, flags, raw Hugging Face and OpenRouter signals, measured GGUF size, links.	slug, limit (1–100)
GET /api/v1/fit	Fit verdicts for one machine: measured weights + computed context cache + overhead versus usable memory, with plain-language reasons and a best recommendation.	hardware (required), model, context (512–1048576, default 8192), kv (f16 · q8_0 · q4_0)
GET /api/v1/hardware	Curated GPU and Mac profiles: ids for /fit, memory, usable memory after margins, bandwidth.	—
GET /api/v1/prices	Median verified on-demand rental price per GPU class (Vast.ai), USD/hour, with min, p75 and offer counts.	—
GET /api/v1/openapi.json	OpenAPI 3.1 description of all of the above — feed it to a tool-using agent.	—

Reading a response

Every payload is { meta, data }. The meta block is the part that keeps you honest:

{
  "meta": {
    "source": "live",            // "fallback" = demo fixtures, a source was unreachable
    "collectedAt": "2026-…",     // oldest contributing reading; null for curated data
    "license": { "license": "CC BY 4.0", "attribution": "AI Model Radar — https://aimodelradar.dev" }
  },
  "data": [ … ]
}

Field names say what a number is: downloads30d is Hugging Face's rolling 30-day counter, not an all-time total and not unique users; heat is null while a model's history is still collecting — never a low score; fit estimates carry the same margins as the site and say UNKNOWN when a model's attention shape is unpublished. The full rules are on the methodology page.

MCP server

The same data as tools for AI assistants, over the Model Context Protocol (Streamable HTTP, stateless, no auth):

https://aimodelradar.dev/api/mcp

Tools: trending_models, find_fit, gpu_prices, list_hardware. Results are the JSON payloads above, provenance included, so an assistant can quote a collection time with every number.

Claude Desktop, Cursor and other Streamable-HTTP clients

{
  "mcpServers": {
    "ai-model-radar": { "url": "https://aimodelradar.dev/api/mcp" }
  }
}

stdio-only clients

{
  "mcpServers": {
    "ai-model-radar": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://aimodelradar.dev/api/mcp"]
    }
  }
}

Listed in the Official MCP Registry as dev.aimodelradar/ai-model-radar — clients and directories that read the registry find it there automatically.

Prefer plain text? /llms.txt maps the site for language models.

Terms

+ License: our data compilation is CC BY 4.0. Attribute “AI Model Radar (https://aimodelradar.dev)” wherever the numbers appear. Upstream facts keep their own terms: Hugging Face Hub public model metadata (trending, downloads, likes); OpenRouter model catalogue (CC BY 4.0); Vast.ai public marketplace offers (aggregated); Vendor product documentation (hardware facts).
+ Rate limit: 60 requests per minute per client, best-effort. Responses are cacheable for five minutes and the data changes hourly at most — please cache.
+ Stability: the path is versioned. Fields are added, never silently changed; a breaking change means a new version and this page says so first.
+ No benchmarks, no speed claims: the API has the same refusals as the site. If you need quality scores, this is not the source — and we would rather say that than invent one.

Building something with it? We would like to see it — the contact address is in the legal notice.