Skip to main content
Geo-specific inference keeps inference processing for supported serverless models inside one geography, with no GPUs to provision. You send requests to that geography’s API endpoint instead of api.together.ai, using the same API key and model IDs.

Choose a geography and model

Model availability differs by geography:

Send a request

Set your client’s base URL to https://us-api.together.ai/v1 for US processing or https://ca-api.together.ai/v1 for Canadian processing. The examples use the US endpoint and GLM-5.3, which is available in both geographies. To run them in Canada, replace us-api with ca-api.
Requests to us-api.together.ai keep inference processing in the United States; requests to ca-api.together.ai keep it in Canada. Requests to api.together.ai do not guarantee either geography.

Pricing

Both US-only and Canada-only inference cost 1.25× the standard serverless rate (a 25% premium) for input, cached input, and output tokens. See US-only prices and Canada-only prices for per-model rates.

Limitations

  • Inference processing only: The guarantee covers where your request is processed. It doesn’t cover where data is stored, where logs are written, or how network traffic is routed.
  • No fallback outside the selected geography: If a model isn’t available in the selected geography, the request fails with a 404 error of type region_unavailable instead of running somewhere else. If your workload requires processing in a specific geography, send retries to that same endpoint, and don’t fall back to api.together.ai.
For private networking or other data-residency requirements, see privacy and security.