Laguna M.1 pricing & benchmarks
Released Apr 28, 2026 · served by 1 provider
What Laguna M.1 is
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...
- Model ID:
poolside/laguna-m.1 - Modality: text->text
- Tool calling: supported · Structured output: not supported
- Weights:
poolside/Laguna-M.1on Hugging Face
Providers and prices for Laguna M.1
The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.
| Provider | Input | Output | Context | Quant | Uptime 24h | Throughput |
|---|---|---|---|---|---|---|
| Poolsidecheapest | $0.200 | $0.400 | 262K | fp4 | 100.0% | — |
FAQ
How much does the Laguna M.1 API cost?
$0.200 per 1M input tokens and $0.400 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.32.
Is Laguna M.1 free?
No. It is a paid model starting at $0.200 per 1M input tokens, though some providers offer trial credits.
Which provider is cheapest for Laguna M.1?
Poolside at $0.200 input / $0.400 output per 1M tokens (fp4 quantization).
Can I self-host Laguna M.1?
Yes — weights are published as poolside/Laguna-M.1 on Hugging Face, so you can run it on your own hardware.