Skip to main content

Why am I hitting API rate limits, and how do I increase them?

Rate limits cap how many requests and tokens you can send to the Mistral APIs. They are set at the organization level and apply across all your workspaces.

📌 API rate limits are not the same as your Vibe plan budget. Rate limits apply to the developer API / Studio. If you received an email about a Vibe Code CLI usage quota, that is your Vibe plan budget — see the FAQ section below ⬇️.

Why you’re seeing 429 Too Many Requests

The API enforces three limits:

  • Requests per second (RPS) — concurrent requests.

  • Tokens per minute — input + output throughput.

  • Tokens per month — overall consumption cap.

A 429 means you exceeded one of them. Free mode (the default) has the lowest limits, intended for evaluation and prototyping.

🔎 See your current limits, usage, and tier on the Limits page of the Admin Console.

How limits increase: plan and tiers

Rate limits depend on your API plan and usage tier:

  • Free mode (default) — limited limits for testing and prototyping.

  • Scale plan (pay-as-you-go) — unlocks Tier 1 and above.

On the Scale plan, tiers upgrade automatically based on your cumulative billed amount (the running total of your invoices):

Tier

Requirement

Tier 1

Scale upgrade

Tier 2

Over €20 / $20 billed

Tier 3

Over €100 / $100 billed

Tier 4

Over €500 / $500 billed

Higher limits

Over €2,000 / $2,000 billed, then contact support

Once you reach Tier 4 (over €2,000 / $2,000 billed), contact our support team with:

  • your target requests per second,

  • the specific model,

  • your estimated tokens per minute and per month.

🔑 Tiers track cumulative billing from usage, not prepaid credit top-ups. Adding credits does not raise your rate limits — you need to use our services and reach the required total-billing thresholds to unlock the next tier.

FAQ

I got a Vibe Code CLI usage quota email but I only use the API. What does it mean?

This email is about your Vibe plan’s monthly budget, not your API rate limits. It usually means your API key was created as a plan key from Code › Vibe Code CLI, which is tied to your plan’s Vibe budget. When that budget is reached, the plan can stop working until the next billing period.

For API automation, use a pay-as-you-go API key created in the console on Free mode or the Scale plan — not a plan key from Code › Vibe Code CLI. Pay-as-you-go keys are governed by API rate limits, not the Vibe budget.

If your API key returns 401 right after this email, or you can’t tell which key type you have, contact our support team with your organization ID. Never share the key itself.

Where can I see my Vibe and API usage?

View your monthly API and Vibe quota usage (shown as a percentage) at Code › CLIView organization usage.

I prepaid credits but I’m still rate-limited. Why?

Prepaying credits adds funds to your account; it does not change your tier or rate limits. Your tier upgrades only as you consume tokens and reach the required total-billing thresholds on the Scale plan.

Credits are automatically applied as your primary balance before your payment method is charged. If an invoice is issued before you add credits, those credits cannot be used to cover that already-issued invoice.

Prepaid API credits are purchased without VAT. The invoice for the usage of those credits is generated when the credits are consumed.

Why did my limits change after switching models?

Rate limits are applied per model. When a model version is retired and you migrate to a newer one, its limits may differ. Check the Limits page for the new model.

📩 Need a higher limit or facing a production incident? Contact our support team.

Did this answer your question?