Laguna S 2.1
Laguna S 2.1 is Poolside's open model for software engineering (OpenMDW 1.1 licence, July 2026): mixture-of-experts, 118B parameters with about 8B active per token. It was designed for agentic coding and long-horizon work, thinking between tool calls rather than only before answering. The card reports 70.2% on Terminal-Bench 2.1 and 78.5% on SWE-bench Multilingual. Text only. It is fulfilled through global providers under our European contract, and requests go only to backends that do not retain prompts or completions.
model id: laguna-s-2.1
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="laguna-s-2.1", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "laguna-s-2.1", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "laguna-s-2.1", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Price list, updated 12 September 2026. No minimum spend, no subscription.
About the model
- Developer
- Poolside
- Released
- July 2026
- Licence
- OpenMDW-1.1
- Architecture
- mixture of experts · 118B parameters, 8B active per token
- Input
- text
- Reasoning
- switchable per request
- Languages named by the developer
- none named on the model card
Source: the developer's model card, as of 17 September 2026.
Licence: what it means for your company
OpenMDW-1.1. OpenMDW 1.1, a permissive licence for model weights and data: per the developer's card you may use and modify the model and build commercial products on it without asking for permission.
A summary of the licence, not legal advice.
Benchmarks reported by the developer
- Terminal-Bench 2.1
- 70.2 %
- SWE-bench Multilingual
- 78.5 %
Figures from the developer's model card, not our measurement. Source: huggingface.co/poolside/Laguna-S-2.1
Technical details
- Context window
- 1M tokens
- Max output
- 65,536 tokens
- Throughput limit
- 200K tok/min
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- poolside/laguna-s-2.1
- max_tokens
- 1 … 65536
- temperature
- 0 … 2
- top_p
- 0 … 1
- frequency_penalty
- -2 … 2
- presence_penalty
- -2 … 2
- stop
- array
- seed
- integer
This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.
Questions about this model
›Where is Laguna S 2.1 computed?
Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.
›Does Laguna S 2.1 store prompts and completions?
No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.
›How large is the Laguna S 2.1 context window?
1M tokens, with up to 65,536 tokens of output.
›What does Laguna S 2.1 cost?
$0.09 per million input tokens and $0.18 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on Laguna S 2.1?
Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.
›Which languages does Laguna S 2.1 support?
The developer's model card names no languages. Test the model on your own material before relying on it in a particular language.
›Under which licence is Laguna S 2.1 released?
OpenMDW-1.1. OpenMDW 1.1, a permissive licence for model weights and data: per the developer's card you may use and modify the model and build commercial products on it without asking for permission.
›Can reasoning be switched off in Laguna S 2.1?
Yes. Per the developer, thinking can be switched on or off for each request.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Laguna S 2.1 | Poolside | 118B / 8B | 1M | OpenMDW-1.1 | $0.09 |
| gpt-oss-120b | OpenAI | 117B / 5.1B | 128K | Apache-2.0 | $0.11 |
| Nemotron 3 Super 120B A12B | NVIDIA | 120B / 12B | 256K | NVIDIA Nemotron Open Model License | $0.13 |
| Qwen3.8 Flash-Next | Qwen (Alibaba) | 125B / 6B | 256K | Qwen Community License 1.0 | $0.15 |
30 more models behind the same key and the same invoice.
Browse the catalog