Limits last verified Jul 29, 2026

Gemini usage limits

Since May 2026, Gemini uses compute-based limits instead of daily prompt counts: allowances refresh every 5 hours inside a weekly cap. Here is what each tier actually gets — dated and sourced.

Every figure below is dated and linked to its official source. Unpublished caps are marked "Not published" — we never guess. Full cross-provider table: AI usage limits comparison.

Tier-by-tier limits

Side-by-side tracked limits for each tier.

LimitGemini FreeGoogle AI ProAI Ultra
PriceFree$19.99/month$249.99/month
Messages / requests per windowStandard compute allowance4× the standard allowance5×–20× the AI Pro allowance
Context window32K tokens1M tokens1M tokens
Model access——Highest tier, including Deep Think reasoning and agent features; 30TB storage bundle
Deep researchNot publishedNot publishedNot published
Image generationNot publishedNot published—
Agent / tool use—Not published—
When you hit the limitAllowance refreshes every 5 hours, inside an overall weekly cap——

✓ Figures verified Jul 29, 2026 against official provider pages · hover any value for its date · full per-fact dates and sources in the plan sections

Gemini Free: full tracked limits

Free · Official pricing page · Full plan guide

LimitValueVerifiedSource
Usage allowanceStandard compute allowance
Since May 2026 Google uses compute-based limits: the allowance refreshes every 5 hours until a weekly cap, and prompt complexity, features, and chat length all count. Numeric prompt counts are no longer published (previously 5 top-model prompts/day).		✓ Jul 29, 2026Official page
Context window32K tokens✓ Jul 29, 2026Official page
Deep Research reportsNot published
Available on the free tier but may be unavailable during high demand; numeric caps are no longer published (previously 5/month).		✓ Jul 29, 2026Official page
Image generationNot published
Image and video generation draw from the shared compute allowance and 'consume more of your usage'; per-day counts are no longer published (previously up to 100/day).		✓ Jul 29, 2026Official page
At the limitAllowance refreshes every 5 hours, inside an overall weekly cap✓ Jul 29, 2026Official page

Google AI Pro / Gemini Advanced: full tracked limits

$19.99/month · Official pricing page · Full plan guide

LimitValueVerifiedSource
Usage allowance4× the standard allowance
Compute-based since May 2026: refreshes every 5 hours until a weekly cap. Numeric prompt counts are no longer published (previously 100 top-model prompts/day).		✓ Jul 29, 2026Official page
Context window1M tokens
Google cites roughly 1,500 text pages.		✓ Jul 29, 2026Official page
Deep Research reportsNot published
Included with higher availability than free; numeric caps are no longer published (previously 20/day).		✓ Jul 29, 2026Official page
Image generationNot published
Draws from the shared compute allowance; per-day counts are no longer published (previously up to 1,000/day).		✓ Jul 29, 2026Official page
Video generationNot published
Video generation consumes the shared compute allowance (previously ~3 fast-tier generations/day). Bundle also includes 2TB storage and NotebookLM higher limits.		✓ Jul 29, 2026Official page

Google AI Ultra: full tracked limits

$249.99/month · Official pricing page · Full plan guide

LimitValueVerifiedSource
Usage allowance5×–20× the AI Pro allowance
Depends on the Ultra subscription tier. Compute-based since May 2026: refreshes every 5 hours until a weekly cap (previously 500 top-model prompts/day).		✓ Jul 29, 2026Official page
Context window1M tokens✓ Jul 29, 2026Official page
Model accessHighest tier, including Deep Think reasoning and agent features; 30TB storage bundle✓ Jul 29, 2026Official page
Deep Research reportsNot published
Highest availability tier; numeric caps are no longer published (previously 200/day). Deep Think reasoning mode is Ultra-only.		✓ Jul 29, 2026Official page

Recorded limit changes

From the full changelog.

  1. Gemini Free

    In May 2026 Google replaced Gemini's fixed daily prompt counts (5/day free, 100/day AI Pro, 500/day Ultra) with compute-based limits that refresh every 5 hours inside a weekly cap; AI Pro is now '4× standard' and Ultra '5×–20× Pro'.

    Before: Fixed daily prompt counts per tier. After: Compute-based allowance, 5-hour refresh + weekly cap.

    Source

Practical guidance

How these limits play out in real workflows.

Prompt counting is gone — compute is the meter

In May 2026 Google replaced fixed daily quotas (5/100/500 top-model prompts) with compute-based limits: prompt complexity, features used, and chat length all draw from an allowance that refreshes every 5 hours until you hit a weekly cap.

The tier multipliers are the published facts now

Google AI Pro gets 4× the standard allowance; Ultra gets 5×–20× Pro depending on subscription. The other hard numbers that remain: context jumps from 32K tokens free to 1M on paid tiers, and Ultra alone gets the Deep Think reasoning mode.

Heavy media use burns the allowance faster

Image and video generation draw from the same compute pool and 'consume more of your usage' — so a media-heavy day exhausts the allowance far faster than chat. The old per-day image counts (100 free / 1,000 Pro) no longer apply.

FAQ

Answers based on the tracked figures above.

How many Gemini prompts do I get for free?

Google no longer publishes a number. Since May 2026 the free tier has a standard compute allowance that refreshes every 5 hours inside a weekly cap — complex prompts, long chats, and media generation use it up faster. Before the change it was about 5 top-model prompts per day.

What do I get with Google AI Pro?

4× the standard compute allowance, a 1M-token context window (roughly 1,500 pages), Deep Research access, and the 2TB storage bundle for $19.99/month.

What happens when I hit a Gemini limit?

Your allowance refreshes every 5 hours, so you wait for the next window — unless you've also exhausted the weekly cap, which resets on its own schedule.

Related pages

AI usage limits comparisonChatGPT usage limitsClaude usage limitsLimit changelog