Gemini CLI Counts Requests per Day, and Here's How Many Each Sign-In Method Gets

How Gemini CLI counts usage

Google counts Gemini CLI usage in model requests, not prompts. The Gemini Code Assist quotas page says one prompt in Gemini CLI or Code Assist agent mode might result in multiple model requests, and that the two share one quota. Requests are limited per user per day and per user per minute, and Google says requests "are subject to the availability of the service in times of high demand." The daily limit is aggregated across every model version and family used with Gemini CLI or agent mode, such as Pro and Flash, and once it's reached, no further requests can be made through those interfaces to any model until the quota resets.

Limits for each sign-in method

Signing in with a personal Google account on the free Gemini Code Assist for individuals gives up to 1,000 model requests per user per day, spread across the Gemini model family as Gemini CLI decides. Google AI Pro raises that to 1,500 a day and Google AI Ultra to 2,000. The Gemini CLI FAQ says the higher Pro and Ultra limits "are for Gemini 2.5 across both Gemini 2.5 Pro and Flash" and are shared between Gemini CLI and agent mode in the Gemini Code Assist IDE extensions. The quotas page says other consumer tiers, including Google AI Plus, aren't supported.

Organization accounts follow the same pattern. A Gemini Code Assist Standard license gives 1,500 requests per user per day, and Gemini Code Assist Enterprise and Workspace AI Ultra give 2,000. Workspace AI Standard, Workspace AI Plus and AI Expanded aren't supported, and Google says its Gemini for Workspace plans cover web products such as the Gemini web app, not the API usage behind Gemini CLI.

A free Gemini API key gives up to 250 model requests per user per day, and only to the Flash model. With a paid key, the quota varies by pricing tier. The Gemini API rate limits page adds that API limits are set per project rather than per key, that daily request quotas reset at midnight Pacific time, and that current limits can be viewed in Google AI Studio.

Vertex AI works differently. Express Mode lets you use Vertex AI for 90 days before you have to enable billing, with quotas that vary by account. In regular mode, usage is governed by a dynamic shared quota system or by pre-purchased provisioned throughput, and the cost depends on the model and token usage.

What happens when you reach a limit

Gemini CLI tries to keep you working. Its model routing docs say that when the selected model fails, for example because of quota or server errors, the CLI starts a fallback process and by default asks before switching to a fallback model for the current turn or the rest of the session. The core docs add that if the default "pro" model is rate-limited, the CLI switches to the "flash" model for the current session. If requests are still refused, Gemini CLI shows a 429 error, which our explainer on Gemini CLI's 429 RESOURCE_EXHAUSTED error covers in detail.

To see where you stand, the /stats model command shows the current session's token usage along with your overall quota and usage for the supported models, and Gemini CLI also prints a summary of model usage when a session ends.

How to get more

Google lists three routes. The first is a higher plan: Google AI Pro or Ultra for personal accounts, or Workspace AI Ultra or a Gemini Code Assist Standard or Enterprise subscription through an organization. The second is pay-as-you-go. The quotas page says that if you hit your daily request limits or run out of Gemini Pro quota even after upgrading, signing in with a Gemini API key or Vertex AI is "the recommended path for uninterrupted access." Google notes that paying per call can cost more for many small calls, but says it's "the only way to ensure your workflow isn't interrupted by reaching a limit on your quota." The /auth command opens the dialog for changing how you sign in.

The third route is a quota increase. The Gemini Code Assist quotas page says most quotas can be adjusted through the Google Cloud console. On the Gemini API, Google says projects move up usage tiers automatically as spending grows, from Tier 1 once an active billing account is linked to Tier 2 after $100 spent and three days from the first successful payment, and Tier 3 after $1,000 and 30 days.