
poolside/Laguna-XS-2.1
A 33B total parameter Mixture-of-Experts model with 3B activated parameters per token.
Learn more here: http://poolside.ai/blog/introducing-laguna-xs-2-1
Technical report: https://poolside.ai/assets/laguna/laguna-m1-xs2-technical-report.pdf
Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work, achieving 47.6% on SWE-Bench Pro. 256K context length. This model is an upgraded version of Poolside’s Laguna XS.2 model with stronger performance on terminal-style tasks. Licensed under OpenMDW-1.1, an open, permissive license for models from the Linux Foundation.
This model delivers the strongest performance in Poolside’s agent harness, pool, after undergoing agent RL. Poolside’s RL stack is a custom-built system loosely coupling the major components of inference and rollout generation, orchestration of code execution sandboxes, trajectory scoring, buffering and filtering, and distributed training.
Input
# You can use this model with any of the OpenAI clients in any language!
# Simply set the API Key to get started
import os
from openai import OpenAI
model_url = "" # Copy in from API pane in Baseten model dashboard
client = OpenAI(
api_key=os.environ['BASETEN_API_KEY'],
base_url=model_url,
)
response = client.chat.completions.create(
model="poolside/laguna-xs-2.1",
messages=[
{
"role": "user",
"content": "Implement Hello World in Python",
}
],
stream=True,
stream_options={
"include_usage": True,
"continuous_usage_stats": True,
},
top_p=1,
max_tokens=1000,
temperature=1,
presence_penalty=0,
frequency_penalty=0,
)
for chunk in response:
if chunk.choices and chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True)Output
{
"id": "143",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": null,
"message": {
"content": "[Model output here]",
"role": "assistant",
"audio": null,
"function_call": null,
"tool_calls": null
}
}
],
"created": 1741224586,
"model": "",
"object": "chat.completion",
"service_tier": null,
"system_fingerprint": null,
"usage": {
"completion_tokens": 145,
"prompt_tokens": 38,
"total_tokens": 183,
"completion_tokens_details": null,
"prompt_tokens_details": null
}
}