Google: Gemma 4 26B A4B
Analysis Summary
Google: Gemma 4 26B A4B sits in the Specialist tier on our leaderboard, ranked #82 of 525 published models on overall intelligence. At $0.060 input and $0.330 output per 1M tokens, it is among the most expensive on the market. It offers a generous context window for extended reasoning and code review and supports tool use, function calling, and vision.
Editorial notes
Google's Gemma 4 26B A4B is an exceptionally cost-effective open-weight model with multimodal capabilities (text, image, and video input), solid instruction-following, and a large 262K context window ā making it a strong choice for budget-conscious businesses handling content and SEO tasks; its coding and agentic capabilities are more limited, so it's best suited to lighter workloads rather than complex technical applications.
Assessed April 24, 2026
Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?
Performance Profile
Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference ā delivering near-31B quality at..
Capabilities
Performance Indices
Source: Artificial Analysis
Benchmark Scores
Intelligence
Technical
Content
Benchmark data from Artificial Analysis and Hugging Face
How does Google: Gemma 4 26B A4B stack up?
Compare side-by-side with other specialist models.
Model Information
| OpenRouter ID |
google/gemma-4-26b-a4b-it
|
| Provider | |
| Release Date | April 3, 2026 |
| Context Length | 262,144 tokens |
| Status | Active |
Pricing
| Token Type | Cost per 1M tokens | Cost per 1K tokens |
|---|---|---|
| Input | $0.06 | $0.000060 |
| Output | $0.33 | $0.000330 |
Live Performance
Live endpoint metrics ā refreshed every 30 minutes.
