Skip to content

Free LLM API errors · Gemini API · checked 2026-11-13

Gemini API 429 RESOURCE_EXHAUSTED: the fix

HTTP 429 · 429 RESOURCE_EXHAUSTED

You went over a limit of your Google AI Studio project: a per-minute request or token limit, or the daily quota.

Why it happens

  • Per-minute limits (requests or tokens): Google's docs call this rate_limit_exceeded and treat it as transient.
  • The daily quota: quota_exceeded. Retrying before it resets will not work.
  • Limits apply per project, not per key: more keys in the same project do not add more.

How to fix it

  1. Retry with exponential backoff, random jitter and a maximum number of tries — Google's own recommendation for 429 and 503.
  2. If retries keep failing for the rest of the day, it is the daily quota: it resets at midnight Pacific time, or you can request a higher quota.
  3. Check the free tier's conditions before relying on it: Google says the free tier may use your prompts to improve its products and may not be used for apps offered to users in the EEA, Switzerland or the UK.

Questions

Should I retry a Gemini 429 RESOURCE_EXHAUSTED?
Yes, with backoff, if it is the per-minute limit. If it is the daily quota, retrying won't help until it resets.
Do more Gemini API keys give more quota?
Not within the same project: Google applies rate limits per project, not per API key.
When does the Gemini API daily quota reset?
Requests-per-day quotas reset at midnight Pacific time.

Sources

Read on 2026-11-13. Providers change limits and messages often; the linked pages are what applies.

Limits and fine print of Gemini API's free tier: Gemini API free API. Tired of handling these by hand? ZeroLimitAI is one OpenAI-compatible endpoint that moves to the next free model when one of these comes back, and can run on your own Groq or OpenRouter key.

Other Gemini API errors

Stop paying per token.

One endpoint. $0 inference.

Free 7-day API key in a minute · no card. Then $99 once on your own key, or $99 a year.