Where do the models run?

Most chat models, speech and transcription run on Together AI's serverless GPUs, and Kimi K2.7 Code, embeddings and rerank on DeepInfra, both in the United States, behind our gateway (authentication, metering, aliasing, error normalisation). The trust page lists the host and precision of every model. OmniParser runs on our own hardware. If you need a specific region, contact us.