Categories › AI & Agents › Models, LLM APIs, routing, serving, training & GPUs
AI model prices per provider, benchmarks, own AI behavior tests and AI economy data, with sources.
Remote server: your requests and data go to benchgecko.ai. Claude Code: claude mcp add --transport http benchgecko https://benchgecko.ai/api/mcp · Claude app: Settings → Connectors → Add custom connector.
The tools this server listed when we connected to it, in its own words.
search_models — Find AI models in the BenchGecko catalog by name, slug or lab. Returns slugs to use with get_model, cheapest_provider and compare_models, wiget_model — Core facts for one AI model: BenchGecko score and rank, list price, price at every provider, benchmark scores with their original sources, Gcheapest_provider — Every provider serving a model, sorted by input price per 1M tokens (refreshed daily from provider endpoints), with output price, quantizaticompare_models — Side by side: BenchGecko score, list price, cheapest provider, context window, shared benchmark scores and Gecko Tests grades for two modelsget_gecko_test — Results of one of BenchGecko's own tests (own measurements, CC BY 4.0): who-are-you (Does the model know which lab made it?) world-map (How get_scorecard — BenchGecko Gecko Scorecard: every model across BenchGecko's own profile tests with a letter grade per test and an overall Gecko Score (behavlatest_findings — Latest notable results detected in the Gecko Tests and price data (fixed rules, numbers and quotes from stored results).search — Search BenchGecko models and Gecko Tests. Returns ids for fetch.fetch — Fetch the full record for an id returned by search (model:<slug>, gecko-test:<slug> or scorecard).Not tested by KitScout yet. When our harness runs it, pros, cons and the tasks we tried appear here, with the date and evidence.