# Gemma 4 31B

Gemma 4 31B is a text generation model from Google, available through the Impossibl API. Its published context window is 128,000 tokens. The advertised input rate is $0.99 per million input tokens. The advertised output rate is $1.49 per million output tokens.

- Model identifier: ` google/gemma-4-31b `
- Creator: Google
- Model type: Text generation
- Canonical model page: [Gemma 4 31B](<https://impossibl.com/google/gemma-4-31b>)
- API availability: Listed as serving through Impossibl.
- Creator release date: 2026-04-02

## Capabilities and limits

- Context window: 128,000 tokens
- Maximum output tokens: Not published in the public catalog; this is separate from the context window.
- Inputs: text, image
- Outputs: text
- Tool calling: Not published

## API access

Use ` google/gemma-4-31b ` as the model identifier through the Impossibl API.

Published API endpoints:

- ` /v1/chat/completions `

[API quickstart](<https://impossibl.com/docs/agent-quickstart>) · [Models and billing documentation](<https://impossibl.com/docs/models>)

## Published API prices

All rates are in USD. An unpublished rate is unknown, not zero. Workspace-specific pricing, taxes, balance-purchase fees, billing adjustments, and tool charges can affect the amount paid.

| Usage | Published base rate | Billing unit |
| --- | --- | --- |
| Input | $0.99 | per million input tokens |
| Output | $1.49 | per million output tokens |
| Cache read | Not published | per million cached input tokens |
| Cache write (default retention) | Not published | per million tokens |
| Cache write (one-hour retention) | Not published | per million tokens |
| Audio input | Not published | per million audio input tokens |

## Independent benchmarks

Source: [Artificial Analysis](<https://artificialanalysis.ai/>). Last checked: 2026-09-11T11:21:18.106Z.
Configurations are evaluated separately. API scores retain their original units. Unmeasured scores are omitted.

### Gemma 4 31B (Reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gemma-4-31b>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 15.42 |
| Omniscience Index | -47.93 |
| GPQA | 85.66% |
| Humanity’s Last Exam | 23.63% |
| SciCode | 45.49% |
| CritPt | 1.43% |
| Terminal-Bench v2.1 | 43.45% |
| Terminal-Bench v4.0 | 0.00% |
| Terminal-Bench Hard | 36.36% |
| AA-LCR | 69.67% |
| Harvey LAB | 47.23% |
| GDPval Elo | 755.45 |
| GDP.pdf All-pass | 6.00% |
| AutomationBench Partial | 4.93% |
| MMMU-Pro | 73.41% |
| IFBench | 75.58% |
| Tau2 | 59.94% |
| Tau Banking | 14.85% |
| ITBench | 37.29% |
| coding index (API) | 43.4 |
| agentic index (API) | 6.7 |
| intelligence index (API) | 15.4 |

### Gemma 4 31B (Non-reasoning)

Source: [Evaluation source](<https://artificialanalysis.ai/models/gemma-4-31b-non-reasoning>)

| Benchmark | Score |
| --- | --- |
| Intelligence Index | 13.92 |
| Omniscience Index | -51.68 |
| GPQA | 76.26% |
| Humanity’s Last Exam | 11.82% |
| CritPt | 0.00% |
| Terminal-Bench v2.1 | 29.21% |
| Terminal-Bench Hard | 30.30% |
| AA-LCR | 46.67% |
| GDPval Elo | 691.46 |
| MMMU-Pro | 70.35% |
| IFBench | 53.47% |
| Tau2 | 65.50% |
| Tau Banking | 8.87% |
| coding index (API) | 33.2 |
| intelligence index (API) | 13.9 |

Full benchmark data and breakdowns: [Complete benchmark snapshot](<https://api.impossibl.com/v1/models/google/gemma-4-31b/benchmarks>).


## Availability and retirement

The model is listed as serving. No retirement is announced in the current public catalog.

## Frequently asked questions

### What is Gemma 4 31B?

Gemma 4 31B is a text-generation model from Google, available through the Impossibl API.

### How much does Gemma 4 31B cost?

Gemma 4 31B costs $0.99 per million input tokens and $1.49 per million output tokens through the Impossibl API. All rates are in USD.

### What is the context length of Gemma 4 31B?

Gemma 4 31B has a 128,000-token context window through the Impossibl API.

### What inputs and outputs does Gemma 4 31B support?

Gemma 4 31B accepts text and image as input. Gemma 4 31B returns text.

### How do I use Gemma 4 31B through an API?

Gemma 4 31B is available through the Impossibl API. Use google/gemma-4-31b as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.

### When was Gemma 4 31B released?

Google released Gemma 4 31B on April 2, 2026.

Sources: [Creator release announcement](<https://blog.google/innovation-and-ai/technology/developers-tools/gemma-4/>)

## Sources and related links

Prices, limits, capabilities, endpoints, and availability come from the public Impossibl catalog. Creator documentation supplies descriptions and release dates where available; it does not override the published API offering.

- [Public Impossibl model catalog](<https://api.impossibl.com/v1/models>)
- [Full model directory as JSON](<https://impossibl.com/models.json>)
- [Gemma 4 31B: model details and pricing](<https://impossibl.com/google/gemma-4-31b>)
- [Model directory](<https://impossibl.com/models>)