Overview

Models

Find model IDs, prices, capabilities, and serving hosts.

Call GET /models for IDs, context limits, prices, modalities, and supported parameters. Call GET /models/{id}/endpoints for host prices, quantization, latency, throughput, uptime, and retention. Use a full model ID such as openai/gpt-5.6-luna in the request body. Model availability and host measurements can change, so read the catalog before relying on one route.