Gemma 4 31B

google/gemma-4-31b-it-20260402

Gemma 4 31B is a Google model that accepts image, text, and video inputs and generates text output, with a context length of 262 144 tokens. It supports tools and reasoning, is released with open weights as of 2026‑04‑02, and charges $0.12 per million input tokens and $0.37 per million output tokens.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providergoogle
releasedApr 2, 2026
context262K
input / M$0.12

Specifications

What the API gives you

Context window
262K tokens
Max output
16K tokens
Input price
$0.12 / 1M tokens
Output price
$0.37 / 1M tokens
Cache read
—
Modalities
image, text, video → text
Knowledge cutoff
—
Released
Apr 2, 2026

Recommendation coverage

Where this model appears

  1. #3Best Local LLM for Coding
  2. #4Best LLM for Translation
  3. #4Best LLM for Massive Context
  4. #6Best LLM for RAG & Long Context

Measured evidence

Public benchmark record

LMArena Agent
-13.62026-07-13
LMArena Agent
-142026-07-20
LMArena Text
1442 Elo2026-07-16
LMArena Vision
1270 Elo2026-07-12
LMArena WebDev
1367 Elo2026-07-16
LMArena WebDev
1367 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.