Google: Gemini 3.1 Pro
Try Gemini 3.1 Pro 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/gemini-3.1-pro-preview"
}).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/gemini-3.1-pro-preview"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Gemini 3.1 Pro is Google's most advanced reasoning model, building on the Gemini 3 series with over double the reasoning performance of its predecessor (77.1% on ARC-AGI-2) and a 1M token context window. It features a three-tier thinking system (low, medium, high) for adjustable reasoning depth and is optimized for agentic workflows, software engineering, and complex problem-solving.
Context Window 1M
tokens
Max Output 66K
tokens
Input Cost $2
per million tokens
Output Cost $12
per million tokens
Input text, image, video, audio, pdf
modalities
Tool Use Yes
Knowledge Cutoff Jan 2025
Release Date Feb 19, 2026
Output Speed 122
tokens / sec
Latency 15.32s
time to first token
Try Gemini 3.1 Pro for free
Try Gemini 3.1 Pro instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Gemini 3.1 Pro performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 94.1% |
| Humanity's Last Exam Cross-domain reasoning | 47.0% |
| SciCode Scientific programming | 58.7% |
| IFBench Instruction following | 77.1% |
| LCR Long-context reasoning | 82.0% |
| Terminal-Bench Hard Agentic terminal tasks | 53.8% |
| τ²-Bench Tool use / agents | 95.6% |
Scores sourced from Artificial Analysis.
Find other Google models →
Gemini 3.8 Flash
Gemini 3.8 Flash is Google's workhorse Flash-tier model, released September 2, 2026, three weeks after Gemini 3.7 Flash. It's built for long-horizon software engineering, agentic workflows, and multi-step reasoning in professional domains. Google reports it outperforms 3.7 Flash and other frontier models on DeepSWE v1.1 for autonomous engineering tasks, on Vals Finance Agent V2, and on Harvey's Legal Agent Benchmark. It scores 54.9% on HLE-Verified, and completes more than three times as many tasks as 3.7 Flash in Google's long-running, document-heavy workflow evaluations. It accepts text, image, video, audio, and PDF input with a 1M token context window and 64K token output limit, supports function calling and iterative tool use, and has a March 2026 knowledge cutoff. Priced at $0.75 per million input tokens and $3.75 per million output tokens through 2026, it targets teams running coding agents or document-heavy enterprise workflows.
ChatGemini 3.7 Flash
Gemini 3.7 Flash is Google's workhorse Flash-tier model, released August 13, 2026, three weeks after Gemini 3.6 Flash. It's built for coding and agentic workflows, targeting software engineering, web development, and knowledge-dense domains like finance and law. Google reports gains over Gemini 3.6 Flash on several benchmarks. DeepSWE v1.1 rose from 49.0% to 65.3%, FrontierCode 1.1 from 34.4% to 43.6%, and AutomationBench from 17.0% to 30.4%. On FrontierCode 1.1 it scores above Claude Sonnet 5 (42.7%) and GPT-5.6 Terra (41.3%), though GPT-5.6 Terra edges it out on Terminal-bench 2.1 (87.4% vs 85.8%). It accepts text, image, video, audio, and PDF input with a 1M token context window and 64K token output limit. It supports function calling, search as a tool, and computer use, and has a March 2026 knowledge cutoff. It's priced at roughly half of Gemini 3.6 Flash's rate, fitting teams running coding agents or high-volume document processing.
ChatGemini Robotics ER 2 Preview
Gemini Robotics ER 2 Preview is Google's embodied reasoning model for robotics, available through the Gemini API and Google AI Studio. It takes video, images, audio and text, reasons about a physical scene, plans multi-step tasks, and hands actions off to a vision-language-action model, a robotics API, or developer-defined tools through function calling. Google says it can plan its next step while a robot is moving, works with the Gemini Live API, and can monitor a task in video, detect failures and retry individual steps. It also supports multi-robot coordination. In Google's reported tests it reached 91.3% accuracy at identifying when a key event occurred in a video (mean error 0.96 seconds) and 57.4% on progress classification. It is meant for developers building robot planning, success detection and scene understanding on top of the Gemini API.
Frequently Asked Questions
You can access Gemini 3.1 Pro 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.
Gemini 3.1 Pro 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.
Gemini 3.1 Pro 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 | $2 |
| Output | $12 |
Gemini 3.1 Pro was created by Google and released on Feb 19, 2026.
Gemini 3.1 Pro supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,097 pages of text.
Gemini 3.1 Pro can generate up to 66K tokens in a single response.
Gemini 3.1 Pro has a knowledge cutoff date of Jan 2025. This means the model was trained on data available up to that date.
Gemini 3.1 Pro accepts the following input types: text, image, video, audio, pdf. It produces: text.
Yes, Gemini 3.1 Pro supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Gemini 3.1 Pro scores 29.7 on the Artificial Analysis Intelligence Index, outperforming 83% of tracked models. On coding, it scores 68.8 (outperforms 77% of models).
Yes — the Gemini 3.1 Pro 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 Gemini 3.1 Pro to your app for free
Developers can integrate Gemini 3.1 Pro for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.