What happened?
Without setting the model, it defaults to gemini-3.1-flash-preview, which I have maxed out my usage of for now. I want to use Gemini 3, but I can't figure out how. I'm using an API Key. I can see gemini-3.1-pro listed in /model manage, but am being told it's "not found for API version v1beta".
What did you expect to happen?
Based on the instructions in the Gemini CLI tool, I expected /model set gemini-3.1-pro to allow me to use the tool with the gemini-3.1-pro model. Instead, it shows gemini-3.1-pro as the current model, but I get the following error :
[API Error: models/gemini-3.1-pro is not found for API version v1beta, or is not supported for generateContent. Call ListModels to see the list of available models and their supported methods.]
Client information
- CLI Version: 0.35.3
- Git Commit: 52d1034
- Session ID: 88a84342-d7c1-4fb0-aec3-230b21143e5f
- Operating System: linux v22.19.0
- Sandbox Environment: no sandbox
- Model Version: gemini-3.1-pro
- Auth Type: gemini-api-key
- Memory Usage: 284.7 MB
- Terminal Name: Unknown
- Terminal Background: #282c34
- Kitty Keyboard Protocol: Unsupported
Login information
No response
Anything else we need to know?
I'm using Ubuntu via WSL2 on Windows, if it matters.
What happened?
Without setting the model, it defaults to gemini-3.1-flash-preview, which I have maxed out my usage of for now. I want to use Gemini 3, but I can't figure out how. I'm using an API Key. I can see gemini-3.1-pro listed in
/model manage, but am being told it's "not found for API version v1beta".What did you expect to happen?
Based on the instructions in the Gemini CLI tool, I expected
/model set gemini-3.1-proto allow me to use the tool with the gemini-3.1-pro model. Instead, it showsgemini-3.1-proas the current model, but I get the following error :Client information
Login information
No response
Anything else we need to know?
I'm using Ubuntu via WSL2 on Windows, if it matters.