Live catalog

Every model, one endpoint.

Every model below is live behind one OpenAI-compatible endpoint. Speed (TPS = output tokens per second, TTFT = time to first token) is measured on real traffic over the last 7 days; volume is what we routed in the last 30 days. Click any model for detailed performance charts.

Prices are the providers' list prices per token. Plans are billed in credits; see your plan for each model's credit rates.