modelgrep
P

Poolside: Laguna M.1

poolside/laguna-m.1

ReasoningToolsJSON
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
73
125th fastest
Latency
728ms
first token
Input price
$0.200
95th cheapest
Context
262K
33K max out

How it compares

Faster than60%
of all ranked models
Cheaper than68%
of all ranked models

Overview

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...

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Poolsidefp4$0.200$0.400

Specifications

Context window262K
Max output33K
Knowledge cutoff
Input modalitiestext
Output modalitiestext
Prompt caching
Cache read price$0.100/M
ModeratedNo

Laguna M.1 FAQ

How much does Laguna M.1 cost?

Laguna M.1 costs $0.200 per million input tokens and $0.400 per million output tokens via OpenRouter, making it 95th cheapest of 301 paid models.

How fast is Laguna M.1?

Laguna M.1 generates around 73 tokens per second with 728ms time-to-first-token (p50), the 125th fastest tracked model.

What is Laguna M.1's context window?

Laguna M.1 supports a 262K-token context window and can output up to 33K tokens. It accepts text input.

Compare head-to-head