# Gemma 4 26B A4B IT

Gemma 4 26B A4B IT is an open-weight mixture-of-experts model from Google that activates roughly 4B of its 26B total parameters per forward pass, delivering competitive reasoning quality at lower latency and cost than a comparable dense model.

- **Model ID:** `google/gemma-4-26b-a4b-it`
- **Type:** chat
- **Providers:** novita, parasail, vertex, gmicloud
- **Context window:** 1,048,576
- **Maximum output tokens:** 1,048,576
- **Pricing:** $0.13/1M input tokens, $0.4/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/gemma-4-26b-a4b-it

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'google/gemma-4-26b-a4b-it',
  prompt: 'Why is the sky blue?'
})
```

## About

Gemma 4 26B A4B IT is part of Google's Gemma 4 family, the open-weight counterpart to the proprietary Gemini lineup. Google released it on April 2, 2026 as an instruction-tuned mixture-of-experts (MoE) model built on the same architecture as Gemini 3.

The MoE design is the defining characteristic. Of the 26B total parameters, only roughly 4B are active during any single forward pass. A routing mechanism selects which expert sub-networks to activate for each input, so Gemma 4 26B A4B IT achieves quality comparable to a much larger dense model while using a fraction of the compute per token. This translates to lower latency and higher throughput. See live metrics on this page for current throughput.

Gemma 4 26B A4B IT accepts text and image inputs within a context window of 1.0M tokens and supports over 140 languages. It handles function-calling, agentic workflows, structured JSON output, and system instructions natively. The instruction-tuning (indicated by the `it` suffix) means Gemma 4 26B A4B IT is ready for conversational and task-oriented use out of the box.

Running Gemma 4 26B A4B IT through AI Gateway provides unified billing, observability, automatic retries, and provider failover without requiring infrastructure management.

## What to consider

Evaluate whether the MoE architecture's latency and throughput characteristics fit your workload before selecting a provider variant at production scale.

## When to use

### Best For

- **Latency-sensitive production workloads** where the MoE architecture's lower compute-per-token translates to faster response times
- **Cost-efficient agentic pipelines** that need function-calling and structured output at high request volumes
- **Multilingual applications** serving users across 140+ languages with a single model
- **Vision-language tasks** such as image understanding, visual Q&A, and document analysis within a context window of 1.0M tokens
- **Open-weight workloads** where the ability to inspect model weights matters

### Consider Alternatives When

- You need the highest possible output quality and latency is not a constraint, where the dense Gemma 4 31B or a Gemini model may be more appropriate
- Your task requires native image or audio generation output, which Gemma 4 26B A4B IT does not support
- Your workload is simple classification or extraction where a smaller, cheaper model is sufficient

## Best for

- **Latency-sensitive production workloads:** The MoE architecture's lower compute-per-token translates to faster response times
- **Cost-efficient agentic pipelines:** Need function-calling and structured output at high request volumes
- **Multilingual applications:** Serving users across 140+ languages with a single model
- **Vision-language tasks:** Image understanding, visual Q&A, and document analysis within a context window of 1.0M tokens
- **Open-weight workloads:** The ability to inspect model weights matters

## Consider alternatives

- **Highest output quality needed:** Latency is not a constraint, and the dense Gemma 4 31B or a Gemini model may be more appropriate
- **Native image or audio generation:** Your task requires media output, which Gemma 4 26B A4B IT does not support
- **Simple classification or extraction:** A smaller, cheaper model is sufficient for straightforward workloads

## Frequently asked questions

### What does mixture-of-experts mean for Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT has 26B total parameters split across expert sub-networks. A routing mechanism activates roughly 4B parameters per forward pass, selecting the most relevant experts for each input. This reduces compute per token compared to a dense model of equivalent total size.

### How does Gemma 4 26B A4B IT compare to the dense Gemma 4 31B?

Gemma 4 26B A4B IT prioritizes latency and throughput by activating fewer parameters per token. The dense Gemma 4 31B activates all 31B parameters, targeting higher output quality at the cost of more compute. Choose Gemma 4 26B A4B IT when speed matters and the dense variant when quality is the priority.

### What input modalities does Gemma 4 26B A4B IT support?

Gemma 4 26B A4B IT accepts text and image inputs. It does not generate images or audio. Use it for text generation, visual understanding, and structured output tasks.

### What languages does Gemma 4 26B A4B IT support?

Over 140 languages. The instruction-tuning covers multilingual conversational and task-oriented use cases.

### How do I use Gemma 4 26B A4B IT on AI Gateway?

Set the model to `google/gemma-4-26b-a4b-it` in the AI SDK. AI Gateway handles provider routing, retries, and failover automatically.

### Does Gemma 4 26B A4B IT support function-calling and structured output?

Yes. It supports function-calling for agentic workflows, structured JSON output, and system instructions natively, sharing these capabilities with the Gemini 3 architecture it is built on.

## Links

- [Model page](https://vercel.com/ai-gateway/models/gemma-4-26b-a4b-it)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://novita.ai/models/model-detail/google-gemma-4-26b-a4b-it)
- [Provider pricing](https://novita.ai/pricing)