- Quotas specify the amount of a countable, shared resource that you can use.
- System limits are fixed values that cannot be changed.
Quotas for Gemini Code Assist
Gemini Code Assist enforces quotas for certain features.
| Quota | Value |
|---|---|
| Local codebase awareness | 1,000,000 token context window |
| Code customization repositories | 20,000 |
Quotas for agent mode and Gemini CLI
Quotas for requests from Gemini Code Assist agent mode and Gemini CLI are combined. When in agent mode or when using the Gemini CLI, one prompt might result in multiple model requests.
| Quota | Gemini Code Assist edition or license type | Ways to purchase | Value |
|---|---|---|---|
| Requests per user per minute | For individuals (free) | N/A | 60 |
| Gemini Code Assist via Google AI Pro | Google AI Pro | 120 | |
| Gemini Code Assist via Google AI Ultra | Google AI Ultra | 120 | |
| Standard | Google Developer Program premium or Google Cloud console | 120 | |
| Enterprise via Google Cloud | Google Cloud console | 120 | |
| Requests per user per day | For individuals (free) | N/A | 1000 |
| Gemini Code Assist via Google AI Pro | Google AI Pro | 1500 | |
| Gemini Code Assist via Google AI Ultra | Google AI Ultra | 2000 | |
| Standard | Google Developer Program premium or Google Cloud console | 1500 | |
| Enterprise | Google Cloud console | 2000 |
Quotas for Gemini in BigQuery
For code assistance features, the quota for Gemini Code Assist and Gemini in BigQuery code requests for features like code completion and code generation is the same.
For customers using Gemini in BigQuery with BigQuery on-demand compute or with Enterprise or Enterprise Plus editions, the quotas for advanced features such as data insights are provided based upon the daily average use of TiB scanned or the slot-hours for the last full calendar month. This quota applies to the organization level and is available to all projects in that organization. Quotas are rounded up to the nearest 100 slot-hour usage.
| Quotas per 100 slot-hours (Enterprise or Enterprise Plus edition daily average usage) or per TiB scanned using on-demand compute model | Value |
|---|---|
| Requests per day for chat, visualization, table scans, and other requests that display responses in the Cloud Assist panel in the Google API Console. | 5 |
Example: An organization that has an Enterprise edition reservation with 100 slots as its baseline will use an average of 2,400 slot-hours each day (100 slots * 24 hours = 2,400 slot-hours). As a result, in the following month they get the following daily quotas:
- 120 chat, visualizations, data insights table scans and automated metadata generations per day
If your organization has not purchased any BigQuery Enterprise edition, Enterprise Plus edition slots, or on-demand compute (TiB) until now, then after your first usage you will receive the default quota of the following for the first full calendar month:
- 250 chat, visualizations, data insights table scans, and automated metadata generations per day
If you start using on-demand compute, Enterprise edition or Enterprise Plus edition reservations mid-month, then the default quota applies until the end of the following month.
How to obtain higher daily model request limits
To adjust agent mode and Gemini CLI quotas, individual developers can purchase the Google Developer Program premium, Google AI Pro or Google AI Ultra.
If you are at a business or organization, we recommend purchasing the Standard or Enterprise edition of Gemini Code Assist. For more information about how to manage quotas within Gemini Code Assist Standard or Enterprise, see View and manage quotas.