Skip to main content
The account tier sets the requests per minute and per hour for each model, and, where set, the input and output tokens per hour and per day. A limit is a ceiling, not a guarantee that every request within it succeeds — see Terms of Service.

Tiers

Every account starts on the Core tier. These tiers apply to paid models; free models have their own tiers — see Free models. The figures apply to each model separately. The Tier and limits page on the platform shows the figures for the account: open the account menu (your name at the bottom of the sidebar) and choose Tier and limits. An account with individual limits shows the Custom tier. Requests through OpenRouter or another router follow that router’s limits.

Moving up

  • What counts: usage charged to purchased credits in one calendar month (UTC). The amount of credits bought does not count, and neither do promotional credits.
  • When: any month that reaches the figure counts, including the current one.
  • How: press Request upgrade on Tier and limits or on the Account page (account menu → Account settings), keep Tier upgrade and press Submit request — see Get help. Each request is reviewed. A new tier starts at the beginning of the next month at the earliest.
  • Keeping it: a tier stays with the account. There is no downgrade.
  • More than Scale: in the same form, set Request type to Enterprise API terms. For on-premises or private cloud, see Harbor.

Free models

Models whose ID ends in :free use the Free tier, which every account has next to its paid tier. Paid tiers do not change it, and a tier upgrade request is always for the next paid tier. Fortytwo gives some accounts the Free Community tier, with individual limits. It cannot be requested.

How requests are counted

  • The windows are rolling: the last 60 seconds and the last 60 minutes, not clock minutes.
  • All keys of the account share the limits. Each model has its own count.
  • Every admitted request counts, also one that fails later. A request refused at admission does not count.
  • Over a limit, a request is refused with 429 rate_limit_exceeded and a Retry-After header — see Errors.

Requests running at the same time

A separate limit caps how many requests from one account can run at once for each model, across all keys. It is not published and can change with the load. A request over it fails at once with 429 concurrency_limit_exceeded. The Terms allow Fortytwo to throttle or queue requests for a short time to protect the service; a request can then wait before it starts — see Terms of Service.

Request size

Image limits are on Image input. An image sent as a data URL counts towards the request body.

How long a request may run

A request can run for up to 60 minutes. After that a non-streaming request returns 504 upstream_timeout; a stream ends with an upstream_timeout event. A stream also ends that way after 4 minutes without data — see Streaming.

Model limits

The context window and the max output depend on the model — see Models.
Last modified on November 13, 2026