Plans

An API plan is a flat monthly price for a workspace: unlimited tokens, paced to a cap in tokens per second. The cap is shared by every API key in the workspace, in each region.

What counts

Output tokens count in full. An uncached input token counts as 0.33. Cached input tokens do not count. The cap is shared by every API key in the workspace, and applies in each region separately. Sail keys are paid for by the Sail plan and never count against it.

A request is counted when it ends, however it ends. A plan key has no tokens-per-minute limit; the requests per minute in Rate limits still apply to every key.

Over the cap

Output is paced to the plan's tokens per second across all the workspace's requests, and a request is never refused for the plan. Over the cap, responses slow down; requests at once share it. A prompt does not delay its own first token. It counts when the request ends, so a long uncached prompt slows the workspace's tokens after it.

Up to 8 requests at once per workspace. One more waits up to 60 seconds for a place, then returns 429 with the code rate_limited and a retry-after.

Stream on a plan. A paced answer arrives as it is generated; a request without stream waits for the whole answer at the plan's cap, which on a small tier can be minutes, and counts against your client's timeout.

Reading your usage

Inference responses to the workspace's API keys carry x-ratelimit-limit-plan-tokens-per-second and x-ratelimit-plan-queued-ms. The usage page lists every request with its tokens.

Changing tier

Subscribe from Pricing. To change tier, cancel from Billing, then subscribe to the new tier.

These docs as plain text for coding agents: llms.txt