# In Gemini's rate limiting, is the input token immediately counted toward the TPM when the request is initiated? Or is it asynchronously tallied into the TPM only after the request completes?

**URL:** <https://discuss.ai.google.dev/t/in-geminis-rate-limiting-is-the-input-token-immediately-counted-toward-the-tpm-when-the-request-is-initiated-or-is-it-asynchronously-tallied-into-the-tpm-only-after-the-request-completes/111711>\
**Category:** Gemini API\
**Tags:** rate-limits\
**Created:** [December 11, 2025, 5:33am UTC](https://discuss.ai.google.dev/t/in-geminis-rate-limiting-is-the-input-token-immediately-counted-toward-the-tpm-when-the-request-is-initiated-or-is-it-asynchronously-tallied-into-the-tpm-only-after-the-request-completes/111711 "2025-12-11T05:33:38Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![hh\_yu](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/hh_yu/32/76451_2.png) [@hh\_yu](https://discuss.ai.google.dev/u/hh_yu)\
**Post date:** [December 11, 2025, 5:33am UTC](https://discuss.ai.google.dev/t/in-geminis-rate-limiting-is-the-input-token-immediately-counted-toward-the-tpm-when-the-request-is-initiated-or-is-it-asynchronously-tallied-into-the-tpm-only-after-the-request-completes/111711/1 "2025-12-11T05:33:38Z")

</div>

Documentation on Gemini’s rate limiting is scarce. I’m currently developing a rate limiter for my project, which integrates with numerous models. I need to know: for Gemini, are input tokens counted toward the rate limit TPM when a request is initiated?

---

<div class="post-metadata">

**Author:** ![Nireeksha\_K\_A](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/nireeksha_k_a/32/26043_2.png) [@Nireeksha\_K\_A](https://discuss.ai.google.dev/u/Nireeksha_K_A)\
**Post date:** [December 26, 2025, 5:48am UTC](https://discuss.ai.google.dev/t/in-geminis-rate-limiting-is-the-input-token-immediately-counted-toward-the-tpm-when-the-request-is-initiated-or-is-it-asynchronously-tallied-into-the-tpm-only-after-the-request-completes/111711/3 "2025-12-26T05:48:20Z")

</div>

Hi @hh_yu ,

Apologies for the delayed response. Could you please share whether you’ve noticed any behavior (for example, delayed 429s) that might indicate tokens are accounted for after completion?

Thanks
