all tiers / Google

Gemini API (AI Studio) free tier limits (2026)

free tier api checked against ai.google.dev

free input/output tokens on a subset of gemini models. free-tier rate limits are no longer published in the docs; google says to view them in ai studio.

per minute
per day
per month
other limits / notes from sourceFree tier on gemini-3.8-flash, 3.6-flash, 3.5-flash-lite, 3.1-flash-lite, 3-flash-preview, 2.5-pro/flash/flash-lite, Live/TTS models, gemini-embedding-2, Gemma; NOT free: Gemini 4 Argon, 3.1 Pro Preview, image models. Search + Maps grounding 500 RPD (2.5 Flash/Flash-Lite); per-model RPM/RPD only inside AI Studio
card requiredno
phone required
used for trainingYES outside EEA/CH/UK (human review); in EEA/CH/UK paid-data terms apply
age req (as stated by the source)18+
requirementsbusiness/professional use; EEA end-user apps must use Paid Services
region restrictionsterms (effective 2026-03-23): only Paid Services may be used to make API clients available to users in the EEA, Switzerland or the UK. for users there, paid-services data terms apply to unpaid quota too.

corrected 2026-10-18: gemini-embedding-2 and maps grounding (500 rpd) are free too. terms are 18+. source

models included

notes

not on free tier: gemini-4-argon, gemini-3.1-pro-preview, image models (nano banana), omni flash, veo, lyria. card_required=false because the docs list the free tier qualification as 'active project or free trial' and billing is only needed for tier 1+.

couldn't find these on the official page: phone required. if you can, send the link and we'll check it.

sources

change history

get the diff every monday