Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
- Modalities
- text → text
- In / out per 1M
- Free / Free
- Context
- 262K tokens
- Added
- Apr 28, 2026
- Max output
- 33K tokens
- Tokenizer
- Other
- Reasoning
- optional
Pricing
Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.
| Per 1M tokens | Provider | + 3% fee | You pay |
|---|---|---|---|
| Input | Free | — | Free |
| Output | Free | — | Free |
Providers
One company serves Laguna M.1 (free). Figures are each provider’s own list price per 1M tokens — your OpenKey price is in the card above.
| Provider | Context | Input /M | Output /M |
|---|---|---|---|
| Poolsidefp4 | 262K | Free | Free |
Provider list from the OpenRouter catalog, Jul 28, 2026. All providers
Supported parameters
- include_reasoning
- max_tokens
- reasoning
- temperature
- tool_choice
- tools
Call it
OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use
model poolside/laguna-m.1:free.
curl https://api.openkey.ai/v1/chat/completions \
-H "Authorization: Bearer ***" \
-H "Content-Type: application/json" \
-d '{
"model": "poolside/laguna-m.1:free",
"messages": [{"role": "user", "content": "Hello"}]
}'import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.openkey.ai/v1",
api_key=os.environ["OPENKEY_API_KEY"],
)
completion = client.chat.completions.create(
model="poolside/laguna-m.1:free",
messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.openkey.ai/v1",
apiKey: process.env.OPENKEY_API_KEY,
});
const completion = await client.chat.completions.create({
model: "poolside/laguna-m.1:free",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);About Laguna M.1 (free)
Laguna M.1 (free) is poolside's flagship coding agent model, built for agentic software engineering work rather than general chat. It carries a 262,144-token context window, larger than 56% of catalog models, room for full repos or long diff histories in one call. It supports tool calling and optional reasoning (on by default), and caps output at 32,768 tokens per response. Max completion tokens run 32,768, output modality is text only. This free variant runs at $0 input and $0 output, giving teams a no-cost way to test the same architecture behind poolside's paid Laguna line before committing spend to it.
This is the free release of Laguna M.1 — the paid version costs $0.20/M input and $0.40/M output, so this variant saves 100% of that while keeping the same 262,144-token context window and tool-calling support. That context sits above 56% of catalog models, useful for feeding large codebases into an agentic loop. Reasoning is optional and enabled by default, not forced, so you can turn it off for lower-latency calls. No benchmark scores are published for this model yet.
Questions
- How much does Laguna M.1 (free) cost via API?
- It's $0 per 1M input tokens and $0 per 1M output tokens, on OpenKey or direct from poolside. OpenKey applies its flat 3% fee to provider list price, but 3% of $0 is still $0, so there's no cost difference here versus using poolside directly.
- Is Laguna M.1 (free) free to use?
- Yes — both prompt and completion tokens are priced at $0 per 1M. It's the free counterpart to poolside's paid Laguna M.1, which costs $0.20/M input and $0.40/M output, so you get the same underlying model at no token cost.
- What is Laguna M.1 (free)'s context window?
- It's 262,144 tokens, large enough to hold a sizable codebase, long commit history, or multiple files in a single request. That puts it above 56% of models in the catalog for context length. Max completion length per response is capped at 32,768 tokens.
- Does Laguna M.1 (free) support tool calling and reasoning?
- Yes to both. It supports tool calling (tools, tool_choice parameters) for agentic workflows, and reasoning is available as an optional mode that's enabled by default — you can disable it per request via the reasoning parameter for faster, cheaper-latency responses.
- How does Laguna M.1 (free) compare to the paid Laguna M.1?
- They're the same model architecture with the same 262,144-token context window and tool-calling/reasoning support; the difference is price. The paid version runs $0.20/M input and $0.40/M output, while this free variant charges $0 for both, making it the better choice for testing before switching to paid for production volume.
More from poolside
All poolside models →
poolsideLaguna M.1
Laguna M.1 is the flagship coding agent model from [Poolside](https://poolside.ai/), optimized for complex software engineering tasks. Designed for agentic coding workflows, it supports tool calling and reasoning, with a 256K...
ctx 262K in $0.206 out $0.412
poolsideLaguna XS.2
Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...
ctx 262K in $0.103 out $0.206
poolsideFreeLaguna XS.2 (free)
Laguna XS.2 is the second-generation model in the XS size class from [Poolside](https://poolside.ai/), their efficient coding agent series. It combines tool calling and reasoning capabilities with a compact footprint, offering...
ctx 262K in Free out Free