Get model rankings
Every public model with traffic over the last 7 days, ranked by tokens served: rank, share of tokens, success rate and median time to first token. Success rate and TTFT are null until the model has at least 100 samples in the window: models are compared against each other here, so the floor is higher than for a single model's stats. Samples follow the model uptime rules (one per request, final outcome, caller errors excluded); token share counts the same requests.
Successful response
application/json- response
data*array<>One item per public model with traffic in the window, sorted by rank.
period_days*integerLength of the measurement window in days.
curl -X GET 'https://api.ohmygpt.com/v1/rankings/models'{ "data": [ { "model": "string", "p50_ttft_ms": 0, "rank": 1, "success_rate": 0, "token_share": 0 } ], "period_days": 0}Get model endpoints GET
Lists the provider endpoints that serve a model, cheapest first, with their price, limits, availability and recent measurements in OpenRouter's format. Measurements come from real traffic, are refreshed about once a minute, and are null until an endpoint has enough samples (see each field). Rate limited per IP.
Get model historical stats GET
Returns historical latency, availability, tool-call, structured-output and effective user pricing statistics for a specific model, in two units: `auto` counts each request that left the provider choice to the gateway by the result the caller received, and each provider counts every upstream attempt it was sent. Only rates, percentiles, shares and prices are published, never request or token counts. Each number is null until it rests on enough samples: rates and shares need at least 20 samples, means, percentiles and weighted prices at least 30.