Everything about Gemma 4 31B IT

What you need to know

Released on April 2, 2026, Gemma 4 31B IT is one of the 14 Google DeepMind models tracked on this site. Its weights are published: you can download it and run it on your own servers, or use one of the 45 API providers that list it on models.dev. It has a reasoning mode: it can "think" before answering, which helps with multi-step problems but uses more tokens, and therefore more money. That makes it 6 months old as of October 22, 2026.

We file it under open-weight models (68 models in this category on the site).

Pricing and budget

Gemma 4 31B IT costs $0.14 per million input tokens and $0.40 per million output tokens (median of 45 providers, checked on October 22, 2026).

To put it in perspective: reading 20,000 tokens (about thirty pages) and writing 2,000 costs roughly $0.004; a thousand of those tasks, $3.6.

That is 2.5 times cheaper than the median output price of open-weight models ($1).

To estimate your own budget, use the agent cost calculator.

Measured performance

Epoch AI publishes 2 results for Gemma 4 31B IT on our basket's benchmarks: too few to compute a reliable capability index.

• GPQA Diamond (PhD-level science questions): 75.8% — the best tracked model, Gemini 4 Argon, reaches 96.4%
• OTIS Mock AIME (competition mathematics problems): 73.3% — the best tracked model, GPT-5.5 Pro, reaches 100%

Context and capabilities

Its context window reaches 262,144 tokens, roughly 393 pages of text at 500 words per page: enough for a long report or several contracts at once. A single answer can run to 32,768 tokens.

It accepts as input: text and image. Its knowledge stops at January 2025: beyond that, it needs web search or your documents.

It can call tools (functions, APIs) and return structured JSON output, which makes it a possible foundation for an AI agent.

The weights are published on Hugging Face (google/gemma-4-31B-it). See also our list of open-source models.

What is it good for?

Given its category, Gemma 4 31B IT is mainly aimed at projects where you want control over your data or hosting, or want to adapt the model to your field.

Its very low cost (under half a cent for our sample task) means it can be called thousands of times a day.

Before adopting it, test it on your own examples: benchmarks measure standard tasks, not your job.

Alternatives

In the same category, the models closest to Gemma 4 31B IT are:

• Jamba Mini (AI21 Labs, $0.40 per million output tokens)
• DeepSeek V3.2 (DeepSeek, index 59.8)
• Gemma 4 26B A4B IT (Google DeepMind, $0.34 per million output tokens)
• Nemotron 3.5 Super VL 120B A12B (NVIDIA, $0.50 per million output tokens)