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 tohttps://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.
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
404error of typeregion_unavailableinstead of running somewhere else. If your workload requires processing in a specific geography, send retries to that same endpoint, and don’t fall back toapi.together.ai.