Models

302 models from 6 providers, on one schema and one bill. Every price below is the provider’s own published rate — per million tokens for chat and embeddings, per image, second or document for the models a token price cannot describe.

Compare Rankings

Sort

Relevance Cheapest output Cheapest input Largest context Name Most providers

All 302 models · 6 providers · 6 with a platform key configured

Latency, throughput and uptime are not shown yet

Those are measurements, not vendor claims, and Multigrid has not served enough traffic to publish honest ones. They will appear here — per provider, from real requests — once they exist. Prices, context windows and capabilities above are read straight from each provider’s published documentation. Per-model usage trends appear here once any model has cleared a minimum request count.

Point one endpoint at this catalogue

Signing up takes no card and commits you to nothing — you start at a zero balance, so nothing can be charged until you decide to add credit. Every price above is what that route costs us, with no spread of ours on top, and every request comes back with what it actually cost.

Create an account How billing works