Tokenify

Rate limits and quotas

Every request is admitted against two ceilings — your key's own, and your account's allowance on the model — and the lower one applies.

Per key

LimitDefaultOn exceeding
Requests per minute1,250429 rpm_exceeded, with Retry-After.
Tokens per minute5,000,000429 tpm_exceeded. Counted on the estimated prompt at admission, not after the fact.
Images per minute60429 ipm_exceeded. Image generation only, counted in images rather than tokens.
Active keys per account50409 when creating the fifty-first.

All three ceilings are token buckets that refill continuously, so a burst is absorbed rather than refused at a minute boundary. A key may be given stricter limits than these — worth doing for one handed to a batch job — while raising one above the default is a conversation with support, because the ceiling is our side of a bargain with the model vendor rather than a preference. Set them per key from the keys page, which also shows what each model allows you.

Per model

Each model also carries an allowance for your whole account, counted per model. It is there because the capacity behind a model is finite and shared, and on several models it is the lower of the two ceilings — so a key showing a million tokens a minute can still be refused on a model whose allowance is smaller. Exceeding it is a 429 with model_rpm_exceeded, model_tpm_exceeded or model_ipm_exceeded and a Retry-After; the message names the figure.

Two things follow from this ceiling being per account rather than per key. A second key does not buy a second allowance — the keys share it, which is the point. And it is counted per model, so traffic to one model never spends another’s: when one model is busy, another will usually serve immediately. Your limits on every model are listed on the keys page.

Per request

LimitValue
Request body50 MB
AttachmentsCounted by what they are, not by the size of the file — see below
Context windowThe model's own — up to 1,048,576 tokens
Max outputThe model's own — up to 393,216 tokens
Completions (n)1 — above it is a 400, not a cap
Time to first byteUp to 10 minutes; reasoning models are expected to think
An inline image or document is counted by what it is and not by the bytes that carry it. An image costs an image’s worth of tokens whatever its resolution, and a document is counted by its pages; the base64 in the request body is not prose and is not counted as prose. So a three-megabyte photograph is a few thousand tokens against the context window and against the token-a-minute ceiling, not a million — the same way the model itself counts it. An attachment of a kind we cannot identify is counted by its bytes for the credit held, and not at all for the two ceilings, because a ceiling should never refuse a request on a guess.
max_tokens above a model’s limit is clamped rather than rejected, and the clamped value is what is sent upstream. For a request that switches thinking off on a model that honours that, it makes the reservation a bound on the bill. Otherwise it is a sized estimate: reasoning is not bounded by max_tokens, so the reservation adds a measured allowance for it and an unusually long reasoning run can settle slightly above what was held. The models that reason whatever they are asked — GLM 5.3 Flash — are reserved that way even with thinking off, because there max_tokens bounds nothing. See models and pricing.

Credit, not quota

There is no monthly quota to exhaust. Spending is bounded by your balance: a request whose worst case exceeds it is refused with a 402 before it is sent. That worst case is held for the duration of the request, so concurrent calls cannot each spend the same credit. A balance can still end slightly below zero when a reasoning run settles above the allowance held for it; the shortfall comes off the next top-up rather than being written off, and nothing is cut off mid-stream to prevent it. Turn on automatic top-ups if you would rather not watch the balance, with a daily ceiling you set.

Need more?

The defaults are conservative because they are the ones a new account gets without asking. If you are planning something larger, tell us the shape of it and we will raise them — there is no tier to buy.

Last updated 2026-10-09.