Gemini CLI free tier limits: how much work 1,000 requests a day buys
Google documents the free tier as 1,000 model requests per user per day and 60 per minute, on a personal Google account. The unit is a model request, which is one call to a model. A prompt is not one call. The project's own maintainer put it in writing: "A single prompt could actually trigger dozens of model requests (API calls)."
On the twelve-call agent task this blog has been pricing all summer, a day's quota is 83 finished tasks at the ceiling. Two further things have moved and are missing from most of the articles about this number: the free tier serves Flash models only since 25 March 2026, and the reset window is not documented anywhere.
Updated 14 November 2026. Clixad changed how its free credits work after this post was written. A new account no longer gets the 25,000-credit signup bonus that figures below rely on. Instead every budget model is free up to the daily allowance, seven models where this post may count five, and our own surveys and the daily streak add to that allowance for the day and the next rather than paying credits into the balance. The rest of the post stands as it was written.
What Google publishes
The Gemini CLI quota page lists two unpaid routes, and they are different tiers.
| How you sign in | Per day | Per minute | Models |
|---|---|---|---|
| Personal Google account | 1,000 model requests | 60 model requests | "across the Gemini model family as determined by Gemini CLI" |
| Gemini API key, unpaid | 250 model requests | 10 model requests | "Model requests to Flash model only" |
Note the model column on the first row: Google does not say which model your quota is spent on, because Gemini CLI decides. So the quota converts into a number of calls, not into a known amount of capability.
The per-minute ceiling says something too. At sixty requests a minute, a thousand a day is under 17 minutes of sustained agent work at the rate Google permits. That is a bound rather than a prediction, but it shows how small a daily request count is once an agent makes the requests.
A model request is not a prompt
A maintainer said it in the project's own discussion thread about the daily limit, in July 2025:
"A single prompt could actually trigger dozens of model requests (API calls)."
The same thread clarifies that the thousand is a total "across model calls including Pro (when applicable), Flash and Flash lite", so it is not a per-model allowance either. One counter, every call, whichever model served it.
An earlier post here explains why: you type one instruction, the agent reads a file, edits it, runs the tests, reads the failure, edits again, and each step is a fresh call carrying the entire conversation so far. This page uses that post's task shape: twelve calls with the context resent every round.
| How you sign in | Model requests a day | Twelve-call tasks a day |
|---|---|---|
| Personal Google account | 1,000 | 83 |
| Gemini API key, unpaid | 250 | 20 |
Eighty-three tasks a day is a real allowance. It is just not a thousand things. The gap comes from the unit, the same gap that turns 50 chat requests a month into about four agent tasks at GitHub.
What changed on 25 March 2026
The figure most people are working from is older than the tier it describes. Google's launch announcement in June 2025 offered "access to Gemini 2.5 Pro and its massive 1 million token context window" at "60 model requests per minute and 1,000 requests per day", and called it the industry's largest free allowance. It was.
A service update on the Gemini CLI repository, effective 25 March 2026, states that "Free tier users will be limited to Gemini Flash models" and that "Gemini Pro models will only be accessible via paid subscriptions". The request count survived the change. The capability behind it did not, and a Flash request and a Pro request were never the same thing to begin with.
The quota page and the launch post are both live, both from Google, and a reader who finds the older one first walks away believing the free tier includes a frontier model. Check the date on any allowance you plan around; every source below carries the date it was read.
What the meter cannot tell you
Several things about this limit that ought to be visible are not.
The reset window is undocumented. The quota page publishes the per-day and per-minute ceilings and says nothing about when the day turns over or in which time zone. The Google Cloud quota page it points to says only that quotas reset in alignment with resets for Google Cloud quotas. An issue opened on the repository in March 2026, titled "Quota never resets after hitting daily limit (Gemini Code Assist for individuals)", reports the practical version of that: "Hit the daily quota on Friday. Error shows a reset time, but 3 days later the quota is still blocked." It was closed as not planned. The reset stamp that user saw was in their own local offset, a hint that the window is per account rather than a common midnight.
The CLI's own counter and the enforced quota can disagree. An issue from January
2026 reports the CLI refusing prompts with a usage limit error while its /stats
command showed quota remaining, and concludes that "The discrepancy between local stats reporting
and API response suggests a sync issue or hidden 'preview' constraints not exposed via the /stats
command." The meter lives on the server and the display is a local estimate of it, so the two can differ.
None of this is unique to Google or a sign of bad faith. It is what happens when the rationed thing is counted in a unit the user cannot observe.
The same day, metered in tokens
Our own side needs care, because a request quota and a token balance do not convert into each other. There is no exchange rate between 1,000 model requests and any number of credits, and anyone offering you one has made it up. What can be compared is how many of the same twelve-call task each side finishes in a day.
Clixad meters real tokens. One task costs what its tokens cost, and a free account earns up to 500,000 credits a day by completing advertiser actions in a browser. That is the ceiling below, not a daily expectation: credits arrive on completion, a screenout part way through a survey pays nothing or a small bonus while still taking the minutes, and that is the most common outcome of starting one on any offerwall.
| Model | One task | Tasks in a 500,000-credit day |
|---|---|---|
| GPT-5 Nano | 3,051 credits | 163 |
| GPT-6 Luna | 5,773 credits | 86 |
| Gemini 3.8 Flash | 43,272 credits | 11 |
| Claude Opus 5.5 | 230,760 credits | 2 |
Start with the third row. On Gemini 3.8 Flash, the class of model Google's free tier actually serves, a full day of earning here is 11 tasks and Google's free tier is 83. If Flash-class models do your work, Google's free tier is more generous than ours by more than seven times, it costs no minutes on a survey wall, and the correct advice is to use it.
The other rows show the difference. A token meter prices whatever you point it at, so the same balance reaches Claude Opus 5.5 at two tasks a day and GPT-5 Nano at 163, and you pick the model rather than the CLI. A request quota cannot express that: every call costs one request whatever answered it, which is why the free tier had to be restricted to Flash rather than repriced.
The second difference shows on a task that fails. A run abandoned at step 8 of 12 has spent eight requests on Google's meter and produced nothing. What a stopped task has already cost is measurable in tokens and not in requests.
How to pick
Use Gemini CLI if Flash-class models finish your work. Eighty-three twelve-call tasks a day, no account beyond a Google login, no earning step and no credit card. On that workload nothing here beats it.
Use Clixad if the model matters more than the volume. Fifteen models on one balance, frontier models included, priced per token so a cheap model costs less. A day at the cap is 163 tasks on the cheapest model and two on Claude Opus 5.5.
Use both. They do not share a ceiling, so a blocked quota on one is not a blocked afternoon.
Use neither if your work needs a Pro-class model every day. Google moved those behind a subscription in March 2026, and our free ceiling reaches Claude Opus 5.5 twice a day. At that point you are looking at a paid plan or your own API key, and the shortlist of tools that include inference is the wrong list to be reading.
FAQ
How many requests does the Gemini CLI free tier give you?
Google's quota documentation gives two free routes. A personal Google account (Gemini Code Assist for individuals) gets 1000 model requests / user / day and 60 model requests / user / minute. An unpaid Gemini API key gets 250 model requests / user / day and 10 model requests / user / minute, restricted to Flash. The unit is a model request, not a prompt.
Is 1,000 requests a day the same as 1,000 prompts?
No, and the project says so itself: a maintainer wrote that a single prompt could actually trigger dozens of model requests (API calls). Every file read, command and retry is another call carrying the whole conversation. On the twelve-call task this blog prices, 1,000 model requests is 83 finished tasks a day at most.
Can you still use Gemini Pro models on the free tier?
No. A service update on the Gemini CLI repository, effective 25 March 2026, says free tier users will be limited to Gemini Flash models and Gemini Pro models will only be accessible via paid subscriptions. The June 2025 launch offer of Gemini 2.5 Pro on the free tier, still quoted by review sites, no longer applies.
When does the Gemini CLI daily limit reset?
Google's quota page for Gemini CLI does not say. It gives per-day and per-minute ceilings with no reset window or time zone, and the Google Cloud quota page it links to says only that quotas reset in alignment with resets for Google Cloud quotas. Users report reset stamps in their own local offsets, and a March 2026 issue reported a quota still blocked three days after the stated reset.
What can you use when the Gemini CLI quota runs out?
Wait for the window, pay for a subscription, or use a second agent that does not share the ceiling. Clixad is the last kind: credits metered against real tokens, every model in the catalogue on one balance, earned by completing advertiser actions in a browser. For Flash-model work Google is more generous: a day at our earning cap finishes 11 twelve-call tasks on Gemini 3.8 Flash, and Google's free tier finishes 83.
The companion to this post is when free AI coding tiers reset, and what carries over, which puts the undocumented window above next to the five other free tiers and finds that four of six publish nothing at all. If you are still working out where the free credits come from in the first place, the four sources is the place to start.
Sources
- Google, Gemini CLI: Quotas and pricing, for "1000 model requests / user / day", "60 model requests / user / minute" and "Model requests will be made across the Gemini model family as determined by Gemini CLI" on Gemini Code Assist for individuals, and "250 model requests / user / day", "10 model requests / user / minute" and "Model requests to Flash model only" on an unpaid Gemini API key. The page states no reset window. Read 20 August 2026.
- Gemini CLI maintainer, Clarification on Daily Request Limit, discussion #4122, 14 July 2025, for "A single prompt could actually trigger dozens of model requests (API calls)." and for the daily figure being a total across model calls including Pro, Flash and Flash Lite. Read 20 August 2026.
- Google, Service update: mitigating abuse and prioritizing traffic, discussion #22970, effective 25 March 2026, for "Free tier users will be limited to Gemini Flash models" and "Gemini Pro models will only be accessible via paid subscriptions". Read 20 August 2026.
- Google, Gemini CLI: your open-source AI agent, 25 June 2025, for "60 model requests per minute and 1,000 requests per day", "access to Gemini 2.5 Pro and its massive 1 million token context window" and "Simply login with a personal Google account". Quoted as the launch position, which the March 2026 update supersedes. Read 20 August 2026.
- User report, Quota never resets after hitting daily limit (Gemini Code Assist for individuals), issue #22643, opened 16 March 2026 and closed as not planned, for "Hit the daily quota on Friday. Error shows a reset time, but 3 days later the quota is still blocked." A user's account of their own experience rather than a statement by Google. Read 20 August 2026.
- User report, Incorrect "Usage limit reached" error while /stats shows remaining quota, issue #17081, opened 20 January 2026, for "The discrepancy between local stats reporting and API response suggests a sync issue or hidden 'preview' constraints not exposed via the /stats command." Also a user report. Read 20 August 2026.
- Credit figures and task costs: Clixad's own pricing engine,
packages/pricing, over the model catalogue read from OpenRouter on 26 July 2026, recomputed by the test beside this post. The twelve-call task shape is read from the markup of the earlier post that declared it. - Offerwall payouts: completed offers on our CPX wall have credited from 9,000 to 114,000 credits on completion, with a median of 51,000: 26 completions recorded in our ledger between 27 July 2026 and 12 September 2026, as of 14 September 2026. Payouts vary widely from one offer to the next. Held as
CPX_COMPLETIONSinpackages/pricing.