API

Acesso programático a dados de modelos de IA, benchmarks e preços, exportações CSV abertas e resultados do Gecko Tests. Plano gratuito disponível.

Grátis para todos · uso pessoal, em pesquisa e comercial

$0 · sem chave de API

Todos os endpoints JSON públicos (modelos, preços por provedor, benchmarks, Gecko Tests, descobertas)
Exportações CSV e datasets diários no GitHub (CC BY 4.0)
Servidor MCP para assistentes e agentes de IA
Histórico de preços e fatos datados de empresas

A única condição: exiba "Fonte: BenchGecko" com um link para benchgecko.ai onde quer que mostre os dados (CC BY 4.0).

Atribuição do tier grátis

O acesso grátis à API exige um link visível "Fonte · BenchGecko" em qualquer página que exiba nossos dados.

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

Endpoints

Os exemplos de resposta usam dados reais do BenchGecko em 11 de nov. de 2026; os arrays foram encurtados.

GET/api/v1/models

Listar todos os modelos com notas e preços

Parâmetros

providerstringFiltrar por slug do provedor (ex.: "anthropic")

open_sourcebooleanFiltrar apenas modelos de código aberto

sortstringOrdenar por: avg_score, pricing_input, release_date, context_window

limitnumberResultados por página (padrão 50, máximo 200)

pagenumberNúmero da página (padrão 1)

Resposta

{
  "data": [
    {
      "slug": "claude-fable-5-2",
      "name": "Claude Fable 5.2",
      "provider": "Anthropic",
      "provider_slug": "anthropic",
      "avg_score": 95.4,
      "scores": {
        "mystery-game-puzzles": 88.98,
        "spireclimb": 19.62,
        "chess-puzzles": 77.9
      },
      "pricing": {
        "input": 8,
        "output": 40
      },
      "context_window": 1000000,
      "is_open_source": false,
      "release_date": "2026-11-09",
      "model_type": "multimodal"
    }
  ],
  "meta": {
    "total": 1310,
    "page": 1,
    "limit": 50,
    "pages": 27
  }
}

GET/api/v1/models/:slug

Pegar dados detalhados de um modelo específico

Resposta

{
  "slug": "claude-fable-5-2",
  "name": "Claude Fable 5.2",
  "provider": {
    "name": "Anthropic",
    "slug": "anthropic"
  },
  "avg_score": 95.4,
  "scores": [
    {
      "benchmark": "Mystery Game Puzzles",
      "benchmark_slug": "mystery-game-puzzles",
      "score": 88.98,
      "category": "general"
    },
    {
      "benchmark": "SpireClimb",
      "benchmark_slug": "spireclimb",
      "score": 19.62,
      "category": "knowledge"
    }
  ],
  "pricing": {
    "input": 8,
    "output": 40
  },
  "context_window": 1000000,
  "is_open_source": false,
  "model_type": "multimodal",
  "release_date": "2026-11-09"
}

GET/api/v1/benchmarks

Listar todos os benchmarks com os modelos que mais pontuaram

Parâmetros

categorystringFiltrar por categoria: coding, reasoning, math, knowledge

Resposta

{
  "data": [
    {
      "slug": "anli",
      "name": "ANLI",
      "category": "knowledge",
      "max_score": 100,
      "unit": "%",
      "models_tested": 11,
      "top_models": [
        {
          "name": "GPT-3.5 Turbo (older v0613)",
          "slug": "gpt-3-5-turbo-0613",
          "provider": "OpenAI",
          "score": 37.15
        },
        {
          "name": "phi-3-small 7.4B",
          "slug": "phi-3-small-7-4b",
          "provider": "Microsoft",
          "score": 37.15
        }
      ]
    }
  ]
}

GET/api/v1/compare

Comparar dois ou mais modelos lado a lado

Parâmetros

modelsstringSlugs de modelos separados por vírgula, de 2 a 6 (ex.: "claude-fable-5-2,deepseek-v3-2-speciale")

Resposta

{
  "models": [
    {
      "slug": "claude-fable-5-2",
      "name": "Claude Fable 5.2",
      "provider": "Anthropic",
      "avg_score": 95.4,
      "pricing": {
        "input": 8,
        "output": 40
      },
      "context_window": 1000000,
      "is_open_source": false
    },
    {
      "slug": "deepseek-v3-2-speciale",
      "name": "DeepSeek V3.2 Speciale",
      "provider": "DeepSeek",
      "avg_score": 95.2,
      "pricing": {
        "input": 0.4,
        "output": 1.2
      },
      "context_window": 163840,
      "is_open_source": true
    }
  ],
  "benchmarks": []
}

GET/api/v1/export/:dataset

Dados abertos em CSV (CC BY 4.0): price-history, provider-offers, price-changes, company-facts, mindshare-daily, gpu-rental-daily, world-map. Apenas dados coletados pelo BenchGecko, sem pontuações de benchmarks de terceiros.

GET/api/lab/:test

Resultados do Gecko Tests em JSON: itens de teste, cada resposta e pontuação dos modelos. Testes: who-are-you, tokenizer-tax, knowledge-horizon, censorship-index, model-drift, same-model-different-host. CC BY 4.0.

SDKs, datasets e código aberto

Bibliotecas cliente oficiais, datasets abertos diários no GitHub (CC BY 4.0), espelhos de snapshots no Hugging Face, Kaggle e Harvard Dataverse, e espelhos da documentação.

Explorar o Developer Hub →

Limites de taxa

Sem chave e sem cota rígida. As respostas ficam em cache na borda por até uma hora, então faça cache também do seu lado. Tráfego que prejudique o serviço pode ser bloqueado.

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.