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 (free)

Google· released 2 Apr 2026

google/gemma-4-31b-it:free
Input / 1M tokens
free
Output / 1M tokens
free
Context window262K tokens

Longest answer: 33K tokens

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

About

Gemma 4 31B is a Google model for text and image input with text output. The listed model facts also include video input, a 262,144-token context window, and a maximum output of 32,768 tokens. It supports reasoning mode and tools, and its weights are open. Google’s summary identifies it as a 30.7B dense multimodal Instruct model. Its model ID is google/gemma-4-31b-it:free, and its Hugging Face ID is google/gemma-4-31B-it. It was released on 2026-04-02. The listed official page is on OpenRouter. The listing marks this version free; no per-token input or output prices are provided here. For teams evaluating model fit, the combination of image and video inputs, text responses, long context, and tool support defines its stated capabilities.

Who it is for

It suits builders looking for an open-weight model with text, image, and video inputs, tool support, and reasoning mode. Its free listing may suit teams evaluating a model without a listed token charge.

What is good

  • Open weights are available.
  • Accepts image, text, and video inputs.
  • Context window is 262,144 tokens.
  • Supports tools and reasoning mode.
  • Free listing.

What to know first

  • Maximum output is 32,768 tokens.
  • No per-token prices are listed.

Verdict

Gemma 4 31B pairs multimodal inputs with a long context window and tool support. Its listing is free, though the maximum output is smaller than its context window.

Details

Lab
Googleopenrouter.ai · 3 Oct 2026
Context
262Kopenrouter.ai · 3 Oct 2026
Input price
Freeopenrouter.ai · 3 Oct 2026
Output price
Freeopenrouter.ai · 3 Oct 2026
Max output
32,768 tokensopenrouter.ai · 3 Oct 2026
Inputs
image, text, videoopenrouter.ai · 3 Oct 2026
Open weights
Yesopenrouter.ai · 3 Oct 2026

More longest-context models

See the list
Auto Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterAuto Router (Beta) ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterGrok 4.20 ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIGrok 4.20 Multi-Agent ctx2,000Kin$1.25 / 1Mout$2.5 / 1M SpaceXAIPareto Code Router ctx2,000KinVaries by model routed tooutVaries by model routed to openrouterLlama 4 Scout ctx1,311Kin$0.1 / 1Mout$0.3 / 1M Meta

Listed on Inferse

Sources