Get model endpoints
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.
creator*stringModel creator namespace (e.g. openai, anthropic)
model*stringModel slug (e.g. gpt-4o, claude-sonnet-4)
format?"openrouter"Compatibility parameter; the endpoint always returns the OpenRouter-compatible capability view.
"openrouter"Successful response
application/json- response
data*curl -X GET 'https://api.ohmygpt.com/v1/models/string/string/endpoints'{ "data": { "endpoints": [ { "context_length": 0, "latency_last_30m": { "p50": 0, "p75": 0, "p90": 0, "p95": 0, "p99": 0 }, "max_completion_tokens": 0, "max_prompt_tokens": 0, "model_id": "string", "model_name": "string", "name": "string", "pricing": { "completion": "string", "image": "string", "input_cache_read": "string", "input_cache_write": "string", "internal_reasoning": "string", "prompt": "string", "web_search": "string" }, "provider_name": "string", "quantization": "string", "status": 0, "supports_implicit_caching": true, "tag": "string", "throughput_last_30m": { "p50": 0, "p75": 0, "p90": 0, "p95": 0, "p99": 0 }, "uptime_last_1d": 0, "uptime_last_30m": 0, "uptime_last_5m": 0 } ], "id": "string" }}Get recent model availability GET
Answers whether the model works right now and when it had trouble over the last 72 hours, for the model as a whole and for each provider that served it. Counted the same way as `/v1/models/{creator}/{model}/stats`: `overall` counts every request for the model by the result the caller received, whoever chose the provider; each provider counts every upstream attempt it was sent. Only rates and minute counts are published.
Get model rankings GET
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.