Google: Gemma 4 26B A4B
Try Gemma 4 26B A4B 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-4-26b-a4b-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-4-26b-a4b-it"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Gemma 4 26B A4B is a Mixture-of-Experts (MoE) open model from Google DeepMind, built from the same research as Gemini 3. It has 26B total parameters but activates only 3.8B per forward pass, delivering near-31B-dense quality at a fraction of the compute cost.
The model supports a 256K token context window, multimodal image and text input, built-in step-by-step reasoning (thinking mode), and native function calling for agentic workflows. It currently ranks #6 among open models on the Arena AI text leaderboard with an estimated LMArena score of 1441 — competitive with models many times its active size.
It excels at reasoning, coding, long-context tasks, and structured tool use. It's a strong pick for developers who need high throughput and low latency without sacrificing capability.
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
Try Gemma 4 26B A4B for free
Try Gemma 4 26B A4B instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Gemma 4 26B A4B performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 79.2% |
| Humanity's Last Exam Cross-domain reasoning | 19.3% |
| SciCode Scientific programming | 40.0% |
| IFBench Instruction following | 72.4% |
| LCR Long-context reasoning | 65.7% |
| Terminal-Bench Hard Agentic terminal tasks | 13.6% |
| τ²-Bench Tool use / agents | 43.6% |
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 3.5 Flash-Lite
Gemini 3.5 Flash-Lite is Google's fastest and most cost-efficient model in the Gemini 3.5 series, built for high-throughput, low-latency workloads. It scores 54% on Terminal-Bench 2.1 and 72.2% on GDM-MRCR v2, up from 31% and 60.1% for Gemini 3.1 Flash-Lite. It also outperforms the larger Gemini 3 Flash on SWE-Bench Pro (54.2% vs. 49.6%) and OSWorld-Verified (74.0% vs. 65.1%), while generating output at roughly 350 tokens per second. It supports text, image, video, audio, and PDF input with a 1M token context window, configurable thinking levels, and function calling, including computer use as a built-in tool. It's suited for agentic search, document processing, and other high-volume tasks where throughput and cost matter more than maximum reasoning depth.
Frequently Asked Questions
You can access Gemma 4 26B A4B 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 26B A4B 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 26B A4B 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 26B A4B was created by Google and released on Apr 2, 2026.
Gemma 4 26B A4B supports a context window of 262K tokens. For reference, that is roughly equivalent to 524 pages of text.
Gemma 4 26B A4B can generate up to 8K tokens in a single response.
Gemma 4 26B A4B has a knowledge cutoff date of Jan 2025. This means the model was trained on data available up to that date.
Gemma 4 26B A4B accepts the following input types: text, image. It produces: text.
Yes, Gemma 4 26B A4B supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Gemma 4 26B A4B scores 16.7 on the Artificial Analysis Intelligence Index, outperforming 61% of tracked models. On coding, it scores 39.3 (outperforms 44% of models).
Yes — the Gemma 4 26B A4B 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 26B A4B to your app for free
Developers can integrate Gemma 4 26B A4B for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.