Limited data
This model hasn't been fully benchmarked yet. Quality scores, speed, and latency data are unavailable.
Google: Gemma 4 31B
Google: Gemma 4 31B is a multimodal AI model by Google. It features a 262K token context window, $0.12/1M input tokens pricing.
Strengths
- +Large context window (262K)
- +Very affordable pricing ($0.12/1M tokens)
- +Supports image input (vision)
Weaknesses
- -No benchmark data available
Pricing per 1M Tokens
| Input (Prompt) | $0.12 |
| Output (Completion) | $0.35 |
| Cache Read | $0.09 |
| Cache Write | Free |
Specifications
| Context Length | 262K |
| Max Output Tokens | 262K |
| Input Modalities | Image + Text + Video |
| Output Modalities | Text |
| Tokenizer | Gemma |
Compare Google: Gemma 4 31B with:
Alternatives to Google: Gemma 4 31B
More from Google
Frequently Asked Questions
How much does Google: Gemma 4 31B cost?
Google: Gemma 4 31B costs $0.12/1M input tokens and $0.35/1M output tokens.
What is Google: Gemma 4 31B's context window?
Google: Gemma 4 31B supports a context window of 262K tokens, which is approximately 131 pages of text.
Is there a free version of Google: Gemma 4 31B?
No, Google: Gemma 4 31B is a paid model. Check the free models page for zero-cost alternatives.
What are alternatives to Google: Gemma 4 31B?
See the alternatives section above for models with similar capabilities. You can also compare Google: Gemma 4 31B head-to-head with any model on our comparison page.
Last updated: