gemma-4-31b
By Google
Reads images: a question can carry pictures.
Model name for the API
gemma-4-31b- Uptime, last 3 days
- 98%
- 102 calls counted
- Price per reply
- Free
- Limited by number of calls
Your chats and training
Not used for training.
The company that answers for this model states in its own terms that it does not use prompts or replies to train its models.
Which company answers for a model is not published here, so this says what the policy is, not whose it is. Checked against their terms on Nov 14, 2026.
Model facts
- Context length
- 256K tokens
- Longest reply
- 256K tokens
- Calls tools
- Yes
- Knowledge cutoff
- Jan 2025
- Released
- 2 Apr 2026
- Open weights
- Yes
Specs come from the models.dev open dataset, read once a day.
Call it through the API
import requests response = requests.post( "https://onomeo.com/v1/chat/completions", headers={"Authorization": "Bearer YOUR_API_KEY"}, json={"model": "gemma-4-31b", "messages": [ {"role": "user", "content": "Hello!"} ]} ) print(response.json())
More from Google
- gemini-3.8-flash$5.63Reference price per million output tokensNo uptime data yet
- gemini-4-hydrogen$11.25Reference price per million output tokensNo uptime data yet
- gemini-4-argon$15.00Reference price per million output tokensNo uptime data yet
- gemini-4-carbon$15.00Reference price per million output tokensNo uptime data yet
Other free models
gemma-4-31b against other models
Figures come from real calls made through this site. Models are served by third-party providers and may slow down or be withdrawn; this page follows those changes.