API

Programmatic access to AI model, benchmark and pricing data, open CSV exports and Gecko Tests results. Free tier available.

Free for everyone · personal, research and commercial use

$0 · no API key

Every public JSON endpoint (models, prices per provider, benchmarks, Gecko Tests, findings)
CSV exports and daily datasets on GitHub (CC BY 4.0)
MCP server for AI assistants and agents
Price history and dated company facts

The only condition: show "Source: BenchGecko" with a link to benchgecko.ai wherever you display the data (CC BY 4.0).

Free Tier Attribution

Free API access requires a visible "Source: BenchGecko" link on any page displaying our data.

<a href="https://benchgecko.ai">Source: BenchGecko</a>

Endpoints

Example responses use real BenchGecko data as of Oct 5, 2026; arrays are shortened.

GET/api/v1/models

List all models with scores and pricing

Parameters

providerstringFilter by provider slug (e.g. "anthropic")

open_sourcebooleanFilter open source models only

sortstringSort by: avg_score, pricing_input, release_date, context_window

limitnumberResults per page (default 50, max 200)

pagenumberPage number (default 1)

Response

{
  "data": [
    {
      "slug": "gpt-5-5-pro",
      "name": "GPT-5.5 Pro",
      "provider": "OpenAI",
      "provider_slug": "openai",
      "avg_score": 99.9,
      "scores": {
        "gpqa-diamond": 94.2
      },
      "pricing": {
        "input": 30,
        "output": 180
      },
      "context_window": 400000,
      "is_open_source": false,
      "release_date": "2026-04-23",
      "model_type": "text"
    }
  ],
  "meta": {
    "total": 1235,
    "page": 1,
    "limit": 50,
    "pages": 25
  }
}

GET/api/v1/models/:slug

Get detailed data for a single model

Response

{
  "slug": "gpt-5-5-pro",
  "name": "GPT-5.5 Pro",
  "provider": {
    "name": "OpenAI",
    "slug": "openai"
  },
  "avg_score": 99.9,
  "scores": [
    {
      "benchmark": "GPQA diamond",
      "benchmark_slug": "gpqa-diamond",
      "score": 94.2,
      "category": "knowledge"
    }
  ],
  "pricing": {
    "input": 30,
    "output": 180
  },
  "context_window": 400000,
  "is_open_source": false,
  "model_type": "text",
  "release_date": "2026-04-23"
}

GET/api/v1/benchmarks

List all benchmarks with top-scoring models

Parameters

categorystringFilter by category: coding, reasoning, math, knowledge

Response

{
  "data": [
    {
      "slug": "gpqa-diamond",
      "name": "GPQA diamond",
      "category": "knowledge",
      "max_score": 100,
      "unit": "%",
      "models_tested": 169,
      "top_models": [
        {
          "name": "Claude Mythos Preview",
          "slug": "claude-mythos-preview",
          "provider": "Anthropic",
          "score": 94.5
        },
        {
          "name": "GPT-6 Astra",
          "slug": "gpt-6-astra",
          "provider": "OpenAI",
          "score": 94.36
        }
      ]
    }
  ]
}

GET/api/v1/compare

Compare two or more models head-to-head

Parameters

modelsstringComma-separated model slugs, 2 to 6 (e.g. "gpt-5-5-pro,claude-mythos-preview")

Response

{
  "models": [
    {
      "slug": "gpt-5-5-pro",
      "name": "GPT-5.5 Pro",
      "provider": "OpenAI",
      "avg_score": 99.9,
      "pricing": {
        "input": 30,
        "output": 180
      },
      "context_window": 400000,
      "is_open_source": false
    },
    {
      "slug": "claude-mythos-preview",
      "name": "Claude Mythos Preview",
      "provider": "Anthropic",
      "avg_score": 99.8,
      "pricing": {
        "input": null,
        "output": null
      },
      "context_window": 1000000,
      "is_open_source": false
    }
  ],
  "benchmarks": [
    {
      "name": "GPQA diamond",
      "slug": "gpqa-diamond",
      "category": "knowledge",
      "scores": {
        "gpt-5-5-pro": 94.2,
        "claude-mythos-preview": 94.5
      }
    }
  ]
}

GET/api/v1/export/:dataset

Open data as CSV (CC BY 4.0): price-history, provider-offers, price-changes, company-facts, mindshare-daily, gpu-rental-daily, world-map. BenchGecko-collected data only, no third-party benchmark scores.

GET/api/lab/:test

Gecko Tests results as JSON: test items, every model answer and score. Tests: who-are-you, tokenizer-tax, knowledge-horizon, censorship-index, model-drift, same-model-different-host. CC BY 4.0.

SDKs, Datasets & Open Source

Official client libraries, daily open datasets on GitHub (CC BY 4.0), snapshot mirrors on Hugging Face, Kaggle and Harvard Dataverse, and documentation mirrors.

Explore the Developer Hub →

Rate Limits

No key and no hard quota. Responses are cached at the edge for up to an hour, so cache on your side too. Traffic that harms the service may be blocked.

AI assistants and agents

BenchGecko is built to be quoted. Every JSON response includes source, url, as_of, license, attribution and a ready-made cite string. Model, test and scorecard pages link their JSON with <link rel="alternate" type="application/json">.

Remote MCP server

https://benchgecko.ai/api/mcp

Streamable HTTP, stateless, read-only, no key needed. Every tool result ends with “Source: BenchGecko · <url>”.

search_models · Search AI models
get_model · Get model facts
cheapest_provider · Cheapest provider for a model
compare_models · Compare two models
get_gecko_test · Gecko Test results
get_scorecard · Gecko Scorecard
latest_findings · Latest findings
search · Search BenchGecko
fetch · Fetch a BenchGecko record

Claude (claude.ai, Claude Desktop)

Settings · Connectors · Add custom connector, then paste the URL above. For older Claude Desktop builds, use the mcp-remote bridge in claude_desktop_config.json:

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

Claude Code

claude mcp add --transport http benchgecko https://benchgecko.ai/api/mcp

Cursor (.cursor/mcp.json) and other clients with remote MCP

{
  "mcpServers": {
    "benchgecko": {
      "url": "https://benchgecko.ai/api/mcp"
    }
  }
}

ChatGPT

Settings · Connectors · Create (developer mode), server URL above, no authentication. The search and fetch tools follow the ChatGPT connector format.

Test it

curl -s https://benchgecko.ai/api/mcp -H 'Content-Type: application/json' -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"cheapest_provider","arguments":{"model":"deepseek-v4-pro"}}}'

/openapi.json

OpenAPI 3.1 for every public read endpoint

/llms.txt

What BenchGecko is, how to cite it, live Gecko Tests snapshot

/llms-full.txt

Every test result, price spreads, companies, GPU rental, glossary

JSON with as-of dates and citations

/api/v1/models/<slug>One model: BenchGecko score and rank, list price, price at every provider, benchmark scores with their source, Gecko Tests grades, as-of dates

/api/v1/models?q=<name>Search the live catalog (or list with provider, open_source, sort)

/api/v1/compare?models=a,b2 to 6 models side by side

/api/v1/price-history/<slug>List price history (add ?envelope=1 for source and as-of fields)

/api/v1/gecko-testsEvery Gecko Test with its latest headline, the scorecard top line and the latest findings

/api/v1/gecko-tests/<test>Per-model results of one test, or the scorecard

/api/lab/<test>Full open dataset: items, runs and every model answer

/api/v1/findingsLatest notable results

/api/v1/export/<dataset>CSV exports (CC BY 4.0), mirrored daily to github.com/BenchGecko/datasets

License: data BenchGecko collects or measures itself (prices per provider, price history, Gecko Tests, mindshare, GPU rental) is CC BY 4.0. Benchmark scores are aggregated from public leaderboards and keep their original source. Credit “Source: BenchGecko” with a link.