ZMIME
Google · Released Apr 2, 2026

Gemma 4 26B A4B IT

Open Gemma instruction model for efficient chat and self-hosted deployments.

  • Open weights
  • Reasoning
  • Tool calling
  • Vision
Capability
141.6ECI · #105 of 158
Input
$0.112per 1M tokens
Output
$0.40per 1M tokens
Context
262K33K max output
Pricing

What it costs

Input
$0.112per million tokens
Output
$0.40per million tokens
Blended (3:1)
$0.184cheaper than 77% of priced models

Typical monthly bills

Monthly usageEstimated cost
Side project2M input + 0.5M output tokens$0.424
Team assistant25M input + 5M output tokens$4.80
Production app250M input + 50M output tokens$48.05

Median of 29 paid API providers on models.dev; Google also offers it free on Google.

Capability

Independent benchmarks

141.6Epoch Capabilities Index
#105 of 158 scored models
68Median 147174

The shaded band is Epoch AI’s confidence range (139.1–144.0); the tick marks the median scored model.

  • GPQA DiamondGraduate-level science questions · minimal setting73.2%
  • OTIS Mock AIME 2024–2025Competition mathematics · minimal setting82.2%

Scores from Epoch AI, run independently of Google.

Specifications

The details

Lab
Google
Released
Apr 2, 2026
Context window
262,144 tokens
Max output
32,768 tokens
Inputs
Text, Images
Output
Text
Reasoning
Can be switched on or off
Tool calling
Yes
Structured output
Yes
API model ID
gemma-4-26b-a4b-iton Google
Availability
33 API providerslisted on models.dev

Google model documentation

Same lab

More from Google

Questions

About Gemma 4 26B A4B IT

How much does Gemma 4 26B A4B IT cost?

Gemma 4 26B A4B IT costs $0.112 input / $0.40 output per million tokens (median across 29 API providers; free on Google). At a 3:1 input-to-output mix that is $0.184 per million tokens, cheaper than 77% of the 469 priced models we track.

What is the context window of Gemma 4 26B A4B IT?

Gemma 4 26B A4B IT accepts up to 262,144 tokens per request and can write up to 32,768 tokens in one response.

How good is Gemma 4 26B A4B IT?

Epoch AI gives Gemma 4 26B A4B IT a Capabilities Index score of 141.6 (likely range 139.1–144.0), ranking it #105 of 158 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 73.2%, OTIS Mock AIME 2024–2025 82.2%.

Is Gemma 4 26B A4B IT open source?

Yes. Google publishes the weights, so it can be downloaded and self-hosted.

What inputs does Gemma 4 26B A4B IT support?

Gemma 4 26B A4B IT accepts text and images and replies in text. It is a reasoning model, supports tool calling and can return structured JSON output.

When was Gemma 4 26B A4B IT released?

Google released Gemma 4 26B A4B IT on Apr 2, 2026.

What are the best alternatives to Gemma 4 26B A4B IT?

The closest current models from other labs on capability, price and release date are Qwen3.5 Flash (Alibaba (Qwen), ECI 143.9, $0.10 / $0.40), DeepSeek V4 Flash (DeepSeek, ECI 146.8, $0.14 / $0.28), GPT OSS 120B (OpenAI, ECI 140.2, $0.15 / $0.60) and GLM-4.7 (Z.ai (Zhipu), ECI 143.4, $0.60 / $2.20).