Issue Station
Sign In
Tools hereToolbox

gemini-cli - 💡(How to fix) Fix Cant search the web because flash model is out of usage [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
google-gemini/gemini-cli#25763•Fetched 2026-04-22 08:03:22
View on GitHub
Comments
0
Participants
1
Timeline
1
Reactions
0
Author
domedavdomedav
Participants
domedavdomedav
Timeline (top)
labeled ×1

Root Cause

yes, this is a termux fork, because the official client can not run under termux. however, this does not invalidate this report.

Code Example

> /about
│ CLI Version                     0.37.1-termux                                               │
│ Git Commit                      b4d7f04d9                                                   │
│ Model                           gemini-2.5-flash-lite                                       │
│ Sandbox                         no sandbox                                                  │
│ OS                              linux                                                       │
│ Auth Method                     Signed in with Google (huaweishitbox2@gmail.com)            │
│ Tier                            Gemini Code Assist for individuals                          │
RAW_BUFFERClick to expand / collapse

What happened?

The 2.5-flash-lite model can not use the websearch tool, when the 3-flash model is out of tokens!

How to reproduce:

Have a usage limit reached 3-flash model, and ask the 2.5-flash-lite model to search the web, the websearch tool will keep retrying the search until the 3-flash model is usable again.

What did you expect to happen?

Expected behaviour:

The 2.5-flash-lite model should be able to search the web, without relying on the 3-flash model in any way.

Client information

<details> <summary>Client Information</summary>

Run gemini to enter the interactive CLI, then run the /about command.

> /about
│ CLI Version                     0.37.1-termux                                               │
│ Git Commit                      b4d7f04d9                                                   │
│ Model                           gemini-2.5-flash-lite                                       │
│ Sandbox                         no sandbox                                                  │
│ OS                              linux                                                       │
│ Auth Method                     Signed in with Google ([email protected])            │
│ Tier                            Gemini Code Assist for individuals                          │

yes, this is a termux fork, because the official client can not run under termux. however, this does not invalidate this report.

</details>

Login information

OAuth (Google Account)

Anything else we need to know?

No response

extent analysis

TL;DR

The 2.5-flash-lite model should be able to search the web independently, without relying on the 3-flash model's availability.

Guidance

  • Verify the websearch tool's configuration to ensure it's not set to fallback or depend on the 3-flash model when the 2.5-flash-lite model is used.
  • Check the usage limits and token management for both models to understand how they interact and potentially cause the observed behavior.
  • Investigate if there's a specific setting or flag that needs to be enabled or disabled to allow the 2.5-flash-lite model to use the websearch tool without relying on the 3-flash model.
  • Test the websearch tool with the 2.5-flash-lite model when the 3-flash model is not at its usage limit to see if the issue persists.

Notes

The issue might be related to how the models are configured to interact with each other or how the websearch tool is designed to handle model availability. Without more information on the internal workings of the models and the websearch tool, it's challenging to provide a definitive fix.

Recommendation

Apply a workaround by investigating and potentially modifying the configuration or settings that control how the 2.5-flash-lite model interacts with the websearch tool and the 3-flash model, as the root cause seems to be related to their interaction rather than a version issue.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#api#ssr#memory leak#API versioning#request timeout

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING