Google: Gemma 4 31B (free)
Gemma 4 31B is a language model developed by Google that can process text, images, and video inputs up to 262144 context characters in length. It supports multiple input modalities and offers tools for reasoning and inference. For those on a tight budget or just starting out with AI models, Gemma 4 31B is worth considering due to its free price point and decent benchmark performance, scoring 56.5 across four independent benchmarks. However, users requiring more advanced capabilities may want to look elsewhere as the model's structured output and open weights are not available.
Benchmark results
Independent, published benchmarks. Blended score 56.5 across 4 benchmarks, last refreshed 2026-09-04. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 49.0 |
| AI Index Coding | software engineering tasks | 71.7 |
| AI Index Agentic | multi-step tool-using tasks | 23.7 |
| EQ-Bench | emotional understanding in dialogue | 70.8 |
- Model ID
- google/gemma-4-31b-it:free
- Vendor
- Released
- April 2026
- Tokenizer
- Gemma
- Input Modalities
- image, text, video
- Output Modalities
- text
- Max Output
- 32,768 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
Strong choice for
Category rankings
Where Google: Gemma 4 31B (free) places across the 5 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #5 | Cheap Bulk InferenceCost · of 25 ranked | 138 |
| #7 | Social Media PostsWriting · of 25 ranked | 120 |
| #7 | Voice Assistant BackendVoice · of 25 ranked | 124 |
| #7 | Self-Hosted / LocalCost · of 25 ranked | 118 |
| #14 | Real-Time ChatLatency · of 25 ranked | 118 |
Similar models
Google: Gemini 3.8 Flash
Google: Gemini 3.8 Flash (batch)
Google: Gemini 3.7 Flash
Google: Gemini 3.7 Flash (batch)
Google: Gemini 3.6 Flash
Google: Gemini 3.6 Flash (batch)
Quick answers
- Is Google: Gemma 4 31B (free) free to use?
- Yes. It is currently listed at no cost per token via OpenRouter, subject to provider rate limits.
- What is Google: Gemma 4 31B (free)'s context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Google: Gemma 4 31B (free) support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Google: Gemma 4 31B (free) process images?
- Yes, it accepts image input.