← Model list
Laguna XS 2.1
poolside·poolside/laguna-xs-2.1·GA·Open weights·laguna series·NEW
Agentic coding model from Poolside in the XS size class for local deployment
At a glance
Official price$0 / $0 per 1M
Cache read $0 · Poolside
Lowest paid$0.06 / $0.12
OpenRouter Gateway
3 more $0 channels
Context262,144
Output limit32,768
Capabilities
✓ Reasoning✓ Tool useStructured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2026-07-02 / 2026-07-02
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 4 providers1 with public prices · 3 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | First-party | Free | — | — | 262,144 | 16,384 | ||
| PoolsideOfficial | First-party | Free | $0 | $0 | 262,144 | 32,768 | ||
| LLMTR | Gateway | Free | — | — | 262,144 | 32,768 | ||
| OpenRouter | Gateway | $0.06 | $0.12 | $0.03 | — | 262,144 | 32,768 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1OpenRouter$14.40
3 more channels offer $0 (Nvidia, Poolside, LLMTR); free tiers usually have rate limits and no SLA, excluded from ranking.
The cheapest paid channel is the only channel.
Benchmark4 items
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Bench Verified | harness: Harbor | 70.9 | resolved | Source ↗ |
| SWE-Bench Multilingual | harness: Harbor | 63.1 | resolve rate | Source ↗ |
| SWE-Bench Pro | harness: Harbor | 47.6 | resolve rate | Source ↗ |
| Terminal-Bench | harness: Harbor · v2.0 | 37.5 | success rate | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Reasoning control
Toggle (on / off)
2 / 4 providers expose no reasoning control (reasoning_options: []).
Related models
Laguna S 2.1 Thinkingsame series$0.10 / $0.20Laguna S 2.1same series$0 / $0Laguna XS 2.1 (free)same series$0 / $0
Price historyone sample accumulated per data sync
Input listOutput listMin blended