Poolside: Laguna M.1

This model is no longer available.

Add AI to your application with Puter.js.

Explore Other Models

Model Card

Laguna M.1 is Poolside's flagship agentic coding model, built for complex, long-horizon software engineering tasks. It's a 225B-parameter Mixture-of-Experts model with 23B activated parameters, offering a 128K context window and support for tool calling and reasoning.

On SWE-bench Verified it scores 72.5%, and it reaches 46.9% on the harder SWE-bench Pro. These results place it in the same tier as far larger models like Qwen3.5 and DeepSeek V4-Flash while using a fraction of the active compute.

Laguna M.1 is purpose-built for agentic workflows — writing code, running tests, inspecting failures, and iterating across files. If you need a model that can plan and execute multi-step engineering tasks end to end, this is Poolside's strongest option.

Context Window 131K

tokens

Max Output 8K

tokens

Input Cost $0

per million tokens

Output Cost $0

per million tokens

Release Date Apr 28, 2026

Code Example

Add AI to your app with the Puter.js AI API, no API keys or setup required.

// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';

puter.ai.chat("Explain quantum computing in simple terms").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").then(response => {
            document.body.innerHTML = response.message.content;
        });
    </script>
</body>
</html>

Frequently Asked Questions

How do I use Laguna M.1?

Laguna M.1 is no longer available through Puter.js. Explore other AI models for alternatives.

What is the pricing for Laguna M.1?

Laguna M.1 costs $0 per 1M input tokens and $0 per 1M output tokens.

	Price per 1M tokens
Input	$0
Output	$0

Who created Laguna M.1?

Laguna M.1 was created by Poolside and released on Apr 28, 2026.

What is the context window of Laguna M.1?

Laguna M.1 supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.

What is the max output length of Laguna M.1?

Laguna M.1 can generate up to 8K tokens in a single response.

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Laguna M.1 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.

Get started with Puter.js

Add AI to your application without worrying about API keys or setup.

Explore Models View Tutorials