Google: Gemma 4 31B
Try Gemma 4 31B for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "google/gemma-4-31b-it"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "google/gemma-4-31b-it"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Gemma 4 31B is a dense multimodal model from Google DeepMind, built on the same research foundation as Gemini 3. It is the most capable model in the Gemma 4 family, accepting text, image, and video input with a 256K-token context window.
It delivers strong benchmark results: 89.2% on AIME 2026, 85.2% on MMLU Pro, 80.0% on LiveCodeBench v6, and 84.3% on GPQA Diamond. On the Arena AI text leaderboard, it ranks as the #3 open model globally, outperforming many models with far higher parameter counts.
Gemma 4 31B features native function calling trained into the model, configurable chain-of-thought reasoning, and structured JSON output — making it especially well-suited for agentic workflows, coding tasks, and multi-turn tool use. It supports over 140 languages and serves as a strong foundation for fine-tuning.
Context Window 262K
tokens
Max Output 8K
tokens
Input Cost $0
per million tokens
Output Cost $0
per million tokens
Input text, image
modalities
Tool Use Yes
Knowledge Cutoff Jan 2025
Release Date Apr 2, 2026
Output Speed 35
tokens / sec
Latency 1.08s
time to first token
Try Gemma 4 31B for free
Try Gemma 4 31B instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Gemma 4 31B performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 85.7% |
| Humanity's Last Exam Cross-domain reasoning | 23.6% |
| SciCode Scientific programming | 45.5% |
| IFBench Instruction following | 75.6% |
| LCR Long-context reasoning | 69.7% |
| Terminal-Bench Hard Agentic terminal tasks | 36.4% |
| τ²-Bench Tool use / agents | 59.9% |
Scores sourced from Artificial Analysis.
Find other Google models →
Gemini 4 Hydrogen
Gemini 4 Hydrogen is a multimodal reasoning model from Google DeepMind, released on November 12, 2026 as part of the Gemini 4 family alongside Gemini 4 Argon and Gemini 4 Carbon. Google describes it as an everyday model for coding and agentic workflows and positions it as the successor to Gemini 3.8 Flash. It accepts text, images, audio, video, and files, returns text, and supports tool calling and four thinking levels (low, medium, high, and xhigh) across a 1M-token context window. Google reports 57% on Terminal-Bench 4.1, up from 18.2% for Gemini 3.8 Flash, with tasks finishing 2.5x faster than 3.8 Flash. On the Artificial Analysis Intelligence Index it scores 51 at high thinking, one point above Gemini 4 Argon. It suits code fixes and debugging, multi-step agents, data analysis, and reports built from PDFs, spreadsheets, audio, and video.
ChatGemini 4 Carbon
Gemini 4 Carbon is Google DeepMind's top model in the Gemini 4 family, announced on October 28, 2026 as a step above Gemini 4 Argon. Google built it for long, multi-step software engineering and defensive cybersecurity, such as finding, validating, and patching vulnerabilities. Google reports 88.2% on SEC-bench Pro, 54.8% on ExploitGym, and 71.0% on CWE-bench. It scores 59 on the Artificial Analysis Intelligence Index v5.0, which Google says places it first on that index. It accepts text, image, audio, video, and file input with a 1M-token context window. Google listed launch pricing of $2 per million input tokens and $10 per million output tokens, rising to $4 and $20 later, with cached input 95% cheaper. On Puter it currently costs $4 per million input tokens and $20 per million output tokens. It suits coding agents, security tooling, and long-document analysis.
ChatGemini 4 Argon
Gemini 4 Argon is Google's flagship Gemini 4 model, announced by Google DeepMind on September 30, 2026. It is aimed at long, multi-step software engineering, legal and finance work, and defensive cybersecurity. Google reports 77.9% on DeepSWE v1.1 (Claude Opus 5.5 74.2%, GPT-6 Astra 74.1%) and 19.6% on Harvey's Legal Agent Benchmark. It trails Opus 5.5 on Terminal-bench 4.0 (57.4% vs 66.4%) and GPT-6 Astra on FrontierSWE v2 (55.0% vs 65.5%). Vals.ai places it first on the Vals Index at 68.9%. Google listed introductory pricing of $2 per million input tokens and $10 per million output tokens, rising to $4 and $20 later. On Puter it costs $4 per million input tokens and $20 per million output tokens. It suits teams running coding agents or document-heavy professional workflows.
Frequently Asked Questions
You can access Gemma 4 31B by Google through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Gemma 4 31B is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
Gemma 4 31B is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0 |
| Output | $0 |
Gemma 4 31B was created by Google and released on Apr 2, 2026.
Gemma 4 31B supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Gemma 4 31B can generate up to 8K tokens in a single response.
Gemma 4 31B has a knowledge cutoff date of Jan 2025. This means the model was trained on data available up to that date.
Gemma 4 31B accepts the following input types: text, image. It produces: text.
Yes, Gemma 4 31B supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Gemma 4 31B scores 4.4 on the Artificial Analysis Intelligence Index, outperforming 3% of tracked models.
Yes — the Gemma 4 31B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Gemma 4 31B to your app for free
Developers can integrate Gemma 4 31B for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.