Gemma 4 31B
Gemma 4 31B is a large language model made by Google, added to the catalog on 2 Apr 2026. It has a context window of 262,144 tokens and costs $0.20 per 1M input tokens and $0.40 per 1M output tokens. It accepts text, images and video and produces text. Typical uses: summarising long documents, answering questions about images and working with video and text prompts.
Price checked · source: OpenRouter
What Gemma 4 31B is
Google Gemma 4 31B is an instruction model that accepts text, image, and video input and produces text. Its context window is 262,144 tokens, and it can generate up to 16,384 output tokens. The large context gives it room to handle lengthy prompts or substantial source material within one context. The catalog describes configurable thinking or reasoning mode, and lists reasoning among its supported capabilities.
The model supports tool use, structured outputs, and response-format controls. These capabilities suit tasks where a request involves source material and calls for a text response in a specified format, or where tool use is part of a workflow. Since it accepts visual input as well as text, it can be used to work with images and video alongside written prompts; its listed output is text. Its context window may also be useful for handling long documents or collections of input material in one request.
The catalog identifies the model’s supported input types, output type, context limit, and interface capabilities, but does not specify particular applications or guarantee a given result. Its stated capabilities provide a basis for choosing it for text work involving visual material, extended context, reasoning, or structured responses. The maximum output length is 16,384 tokens, separate from the 262,144-token context window.
Key features
- Accepts text, image, and video input and produces text
- Has a 262,144-token context window
- Supports configurable thinking or reasoning mode
- Supports tools, structured outputs, and response-format controls
Typical uses
- Summarising long documents
- Answering questions about images
- Working with video and text prompts
- Generating structured text responses
- Tool-assisted text workflows
Gemma 4 31B pricing
US dollars, list price through OpenRouter.
| Item | Standard | Free |
|---|---|---|
| Input, per 1M tokens | $0.20 | $0 |
| Output, per 1M tokens | $0.40 | $0 |
| Variant | Model id |
|---|---|
| Free | google/gemma-4-31b-it:free |
A variant is the same model under another id, with prices or limits of its own. Its prices are the columns of the list above.
No price change since it was added on 2 Apr 2026.
| What a task costs | Cost |
|---|---|
| Answer a short question500 in / 300 out | $0.0002 |
| Summarise a 50-page PDF25,000 in / 800 out | $0.0053 |
| Review a 2,000-line source file30,000 in / 2,000 out | $0.0068 |
| Read a 300-page contract set150,000 in / 1,500 out | $0.031 |
Gemma 4 31B specifications
| Model id | google/gemma-4-31b-it |
|---|---|
| Version | gemma-4-31b-it-20260402 |
| Context window | 262,144 tokensAbout 196,608 English words |
| Max output | 16,384 tokens |
| Knowledge cutoff | Not published |
| Added to catalog | 2 Apr 2026 |
| Input types | image, text, video |
|---|---|
| Output types | text |
| Tool calling | Yes |
| Structured outputs | Yes |
| Reasoning effort control | No |
| Content moderation | Not applied by provider |
Sample outputs
The same prompts are given to every model, and the unedited output is shown with the date it was produced. Upend does not publish leaderboard scores it did not run.
No output has been recorded for Gemma 4 31B yet.
Compare Gemma 4 31B
Side by side with other models: prices, context window, what each accepts and supports, and the same four tasks priced on both.