Paid, cached snapshot of OpenRouter's public model catalog with model IDs, context window, listed input/output token prices, and HTTP catalog-fetch latency. No inference requests are made; the latency metric is not model TTFT or throughput.
AI developer agents and model-routing workflows
Retrieve a small filtered set of public model/pricing metadata in one agent-readable response.
x402-gated JSON subset with explicit model pricing and no inference call; catalog fetch latency clearly distinguished from inference latency.
N/A
No history recorded