Laguna S 2.1

Free
poolside/laguna-s-2.1-free

open-weight agentic coding and long-horizon work.

cmd --model poolside/laguna-s-2.1-free
Intelligence index
not yet scored
Output speed
not yet scored
Input
$0.00 /M
Output
$0.00 /M
Cache read
$0.00 /M
Agent-loop cost
$0.00 /M in
Context window
256K tokens
Released
Modalities

deal spotlight

Every request on Laguna S 2.1 is billed $0.00 — input, output and cache reads alike.

FREE
while capacity lasts
Full terms →
Input $/M
$0.00
Output $/M
$0.00
Cache read $/M
$0.00

vs. the lineup

Laguna S 2.1 beside its stablemates and nearest rivals. The ◆ marks the best value in each column across every row shown.

pin a rival:
ModelIntelligenceCodingSpeedInput $/MOutput $/MBlended $/MContext
Step 3.7 Flash30.939.6391.3$0.20$1.15$0.44256K
Claude Haiku 4.524.196.3$1$5$2200K
Laguna S 2.1$0.00$0.00$0.00256K
DeepSeek V4 Pro (latest)pinned45.359.463.3$0.43$0.87$0.541M
DeepSeek V4 Flash (latest)pinned5269.1115.9$0.14$0.28$0.181M

usage calculator

How far a month of credits goes on Laguna S 2.1.

Input tokensfresh prompt
800
Output tokensmodel reply
180
Cache read tokensre-read context
50K
cost / request $0.00 · in $0.00 · out $0.00 · cache $0.00 per M
Requests / 30 days
free while the deal runs — credits never draw down

what real work costs

Real coding tasks, from a quick lookup to a full-repo agent run — all of them free on Laguna S 2.1 while the deal runs.

TaskTokens in · outLaguna S 2.1Claude Haiku 4.5
Quick lookup / one-liner8K · 1K$0.00$0.0065
Review a 500-line PR60K · 4K$0.00$0.04
Fix a bug (agent loop)180K · 12K$0.00$0.12
Refactor a module320K · 20K$0.00$0.21
Full-repo agent run900K · 45K$0.00$0.49

frequently asked

What is Laguna S 2.1 best for?+
Laguna S 2.1 is the latest coding agent model from Poolside . Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-Bench 2.1 and 40.4% on DeepSWE, making it one of the strongest coding models in its category. Open-weight under the OpenMDW-1.1 license. Laguna S 2.1 is designed for software engineering and agentic coding use cases, and you are responsible for confirming that it is appropriate for your intended application. Laguna S 2.1 is subject to the OpenMDW-1.1 License , and should be used consistently with Poolside's Acceptable Use Policy . We advise against circumventing Laguna S 2.1 safety guardrails without implementing substantially equivalent mitigations appropriate for your use case. Please report security vulnerabilities or safety concerns to [email protected] . If you are using Laguna S 2.1 for free, we may use your inputs and outputs to train and improve our models.
How much does Laguna S 2.1 cost?+
$0.00/M input and $0.00/M output, cache reads $0.00/M. In an agent loop most input is cache-read, so the effective input rate is about $0.00/M.
Which plan do I need?+
Available on Go and above.
How do I switch to it?+
Run cmd --model poolside/laguna-s-2.1-free, or type /model in a session and pick it. You can switch mid-session without losing context.

Ship code that matches your taste

Command Code is the AI coding agent that continuously learns your taste. Start for $1.

Benchmarks from Artificial Analysis (v4.1)commandcode.ai/models/laguna-s-2-1-free