# Gemma 4 31B

Model tracker · checked 2026-10-14 · https://dbggr.dev/models/gemma-4-31b/

Gemma 4 31B is a fast open-weight model from Google, released 31 March 2026. At AWS it costs $0.14 per million input tokens and $0.40 per million output tokens, with a 256K-token context window. 5 providers serve it, and AWS is the cheapest.

- Made by: Alphabet (Google, Google DeepMind, Google Cloud)
- Released: 2026-03-31
- Status: Generally available
- Tier: Fast
- Weights: Open
- Context window: 256,000 tokens
- Input: text, image, video
- API id: google.gemma-4-31b
- Docs: https://huggingface.co/google/gemma-4-31B-it

## Gemma 4 31B price at 5 providers

US dollars per million tokens. Blended is 3 input tokens for every output token, one number to compare on. The cheapest blended price is highlighted.

| Provider | Input | Output | Cached input | Blended | Batch | Checked |
|---|---|---|---|---|---|---|
| AWS | $0.14 | $0.40 | – | $0.205 | – | [2026-10-14](https://aws.amazon.com/bedrock/pricing/) |
| Novita AI | $0.14 | $0.40 | – | $0.205 | – | [2026-10-14](https://novita.ai/pricing) |
| DeepInfra | $0.20 | $0.40 | – | $0.25 | – | [2026-10-14](https://deepinfra.com/pricing) |
| Together AI | $0.39 | $0.97 | – | $0.535 | – | [2026-10-14](https://www.together.ai/pricing) |
| SambaNova | $0.38 | $1.15 | – | $0.573 | – | [2026-10-14](https://cloud.sambanova.ai/pricing) |

- AWS: Amazon Bedrock, US East (N. Virginia), Standard tier. Europe (Frankfurt): $0.17 / $0.48.
- Together AI: Together removed google/gemma-4-31B-it from serverless on 2026-09-15 (deprecations page); the pricing page still lists it.
- SambaNova: Preview model on SambaCloud.

## Price changes

- Until 2026-10-05 at DeepInfra: $0.15 input, $0.40 output per million tokens.

## Models like Gemma 4 31B

| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| Gemma 4 31B | $0.14 | $0.40 | 256K | Open |
| [Claude Haiku 5.5](https://dbggr.dev/models/claude-haiku-5-5/) | $0.10 | $0.50 | 1M | Closed |
| [Ministral 3 14B](https://dbggr.dev/models/ministral-3-14b/) | $0.20 | $0.20 | 256K | Open |
| [GPT-6 Luna](https://dbggr.dev/models/gpt-6-luna/) | $0.10 | $0.50 | 1.1M | Closed |
| [Qwen3.8 Flash](https://dbggr.dev/models/qwen3-8-flash/) | $0.15 | $0.47 | 1M | Closed |
| [GLM-5.3 Flash](https://dbggr.dev/models/glm-5-3-flash/) | $0.15 | $0.50 | 1M | Open |

## FAQ

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

Gemma 4 31B costs $0.14 per million input tokens and $0.40 per million output tokens at AWS. Prices are list prices in US dollars, last checked 14 October 2026.

### What is Gemma 4 31B's context window?

Gemma 4 31B takes up to 256,000 tokens in one request.

### Is Gemma 4 31B open weight?

Yes. Google publishes the weights, so you can run Gemma 4 31B yourself or at any host that serves it.

### Where can I use Gemma 4 31B?

Gemma 4 31B is available from AWS, Novita AI, DeepInfra, Together AI and SambaNova. At AWS, call it as `google.gemma-4-31b`.