Inferse
For vendors
AdvertiseTop spots, featured rows, home sponsor Get listedAdd a product we don't cover yet Claim a listingFree: verify the domain, then correct your page Vendor dashboardNumbers, orders and placements
List your platform
Vendor dashboard

Gemma 4 31B

Google· released 2 Apr 2026

google/gemma-4-31b-it
Input / 1M tokens
$0.09
Output / 1M tokens
$0.34
Context window262K tokens

Longest answer: 16K tokens

reads imagereads textreads videoopen weightstool callingvisionreasoning
See it on openrouter.ai

About

Gemma 4 31B is a Google model in the google family, released on 2026-04-02. Google DeepMind’s Gemma 4 31B Instruct is described as a 30.7B dense multimodal model with text and image input, text output, a 256K-token context window, configurable thinking or reasoning mode, and native function support. The model is open weights, with Hugging Face identifier google/gemma-4-31B-it and model ID google/gemma-4-31b-it. It accepts image, text, and video inputs and returns text. Tools, vision, and reasoning are supported. The maximum output is 16,384 tokens. Pricing is 0.09 USD per 1M tokens for input and 0.34 USD per 1M tokens for output. Google is listed as maker and lab. The official site is the OpenRouter page for this model. Its input coverage includes video in addition to the image and text modalities highlighted in the summary.

Who it is for

Gemma 4 31B suits teams seeking open weights with image, text, and video inputs. It fits applications needing tools, vision, reasoning, configurable thinking, and a 262,144-token context window.

What is good

  • Open weights available
  • 262,144-token context window
  • Supports image, text, and video inputs
  • Tools, vision, and reasoning support
  • Input priced at 0.09 USD per 1M tokens

What to know first

  • Maximum output is 16,384 tokens
  • Output costs 0.34 USD per 1M tokens
  • Text is the only output modality

Verdict

Gemma 4 31B combines open weights with multimodal inputs, reasoning controls, tools, and a large context window. Its listed token prices are 0.09 USD per 1M input tokens and 0.34 USD per 1M output tokens.

Details

Lab
Googleopenrouter.ai · 3 Oct 2026
Context
262Kopenrouter.ai · 3 Oct 2026
Input price
$0.09 / 1Mopenrouter.ai · 3 Oct 2026
Output price
$0.34 / 1Mopenrouter.ai · 3 Oct 2026
Max output
16,384 tokensopenrouter.ai · 3 Oct 2026
Inputs
image, text, videoopenrouter.ai · 3 Oct 2026
Open weights
Yesopenrouter.ai · 3 Oct 2026

More newest models

See the list
Ling 3.1 Flash ctx262KinFreeoutFree inclusionAIApodex 1.1 Mini (free) ctx262KinFreeoutFree ApodexPareto 26.10 Preview ctx1,049Kin$0.8 / 1Mout$3.2 / 1M unbiasedGPT-6.1 Sol ctx1,050Kin$2 / 1Mout$10 / 1M OpenAIGPT-6.1 Sol Pro ctx1,050Kin$2 / 1Mout$10 / 1M OpenAIClaude Sonnet 5.5 ctx1,000Kin$2 / 1Mout$10 / 1M Anthropic

Listed on Inferse

Sources