# Gemma 4 26B A4B

Model tracker · checked 2026-10-14 · https://dbggr.dev/models/gemma-4-26b-a4b/

Gemma 4 26B A4B is a fast open-weight model from Google, released 31 March 2026. It's in preview. At Google it costs $0.15 per million input tokens and $0.60 per million output tokens, with a 262K-token context window. 5 providers serve it; the cheapest is DeepInfra at $0.07 input and $0.34 output.

- Made by: Alphabet (Google, Google DeepMind, Google Cloud)
- Released: 2026-03-31
- Status: Preview
- Tier: Fast
- Weights: Open
- Context window: 262,144 tokens
- Max output: 128,000 tokens
- Input: text, image
- API id: gemma-4-26b-a4b-it-maas
- Docs: https://huggingface.co/google/gemma-4-26B-A4B-it

## Gemma 4 26B A4B 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 |
|---|---|---|---|---|---|---|
| DeepInfra | $0.07 | $0.34 | – | $0.138 | – | [2026-10-14](https://deepinfra.com/pricing) |
| Cloudflare | $0.10 | $0.30 | – | $0.15 | – | [2026-10-14](https://developers.cloudflare.com/workers-ai/platform/pricing/) |
| AWS | $0.13 | $0.40 | – | $0.198 | – | [2026-10-14](https://aws.amazon.com/bedrock/pricing/) |
| Novita AI | $0.13 | $0.40 | – | $0.198 | – | [2026-10-14](https://novita.ai/pricing) |
| Google | $0.15 | $0.60 | $0.015 | $0.262 | – | [2026-10-14](https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing) |

- Cloudflare: Billed in Neurons at $0.011 per 1,000; 10,000 Neurons a day free.
- AWS: Amazon Bedrock, US East (N. Virginia), Standard tier. Europe (Frankfurt): $0.16 / $0.48.
- Google: Listed as Gemma 4 26B on Google Cloud's generative AI pricing page; 26B A4B is the only 26B Gemma 4 model. Savings-plan discounts are listed separately.

## Models like Gemma 4 26B A4B

| Model | Input | Output | Context | Weights |
|---|---|---|---|---|
| Gemma 4 26B A4B | $0.15 | $0.60 | 262K | Open |
| [Mistral Small 4](https://dbggr.dev/models/mistral-small-4/) | $0.15 | $0.60 | 256K | Open |
| [GLM-5.3 Flash](https://dbggr.dev/models/glm-5-3-flash/) | $0.15 | $0.50 | 1M | Open |
| [Qwen3.8 Flash](https://dbggr.dev/models/qwen3-8-flash/) | $0.15 | $0.47 | 1M | Closed |
| [Gemma 4 31B](https://dbggr.dev/models/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 |

## FAQ

### How much does Gemma 4 26B A4B cost?

Gemma 4 26B A4B costs $0.15 per million input tokens and $0.60 per million output tokens at Google, and $0.015 per million cached input tokens. Prices are list prices in US dollars, last checked 14 October 2026.

### What is Gemma 4 26B A4B's context window?

Gemma 4 26B A4B takes up to 262,144 tokens in one request and writes up to 128,000 tokens in one response.

### Is Gemma 4 26B A4B open weight?

It's listed as open weight, but it's still in preview: check Google's announcement for when the weights and licence are published.

### Where can I use Gemma 4 26B A4B?

Gemma 4 26B A4B is available from DeepInfra, Cloudflare, AWS, Novita AI and Google. At Google, call it as `gemma-4-26b-a4b-it-maas`.