Gemma 4 26B A4B
google/gemma-4-26b-a4b-it-20260403
Google's Gemma 4 26B A4B, released on 2026‑04‑03, is a multimodal model that accepts image, text, and video inputs and produces text output. It supports tools and reasoning, provides a context window of 262,144 tokens, and its weights are publicly available. Pricing is $
- tool use
- structured outputs
- reasoning
- open-weight
At a glance
providergoogle
releasedApr 3, 2026
context262K
input / M$0.070
Specifications
What the API gives you
- Context window
- 262K tokens
- Max output
- 16K tokens
- Input price
- $0.070 / 1M tokens
- Output price
- $0.34 / 1M tokens
- Cache read
- —
- Modalities
- image, text, video → text
- Knowledge cutoff
- —
- Released
- Apr 3, 2026
Recommendation coverage
Where this model appears
Measured evidence
Public benchmark record
- LMArena Text
- 1434 Elo2026-07-16
- LMArena Vision
- 1258 Elo2026-07-12
- LMArena WebDev
- 1361 Elo2026-07-16
- LMArena WebDev
- 1360 Elo2026-07-20
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open.
Open-weight model on Hugging Face.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.