- Organizations
- Poolside
- Laguna S 2.1
Laguna S 2.1: API Pricing, Context Window & Benchmarks
Laguna S 2.1 is a language model from Poolside, released in July 2026, with a 1.0M-token context window, and pricing from $0.100/M input, $0.010/M cached input, $0.200/M output.
Laguna S 2.1 is Poolside's most capable Laguna 2.1 model: an open-weight Mixture-of-Experts coding model with 118B total parameters and 8B activated per token (256 routed experts + 1 shared; 48 layers). It targets long-horizon and agentic
Laguna S 2.1 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Laguna S 2.1 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Laguna S 2.1 holds up as conversations get longer.
Quality Tracker
Laguna S 2.1 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
Laguna S 2.1 pricing
Providers
Laguna S 2.1 starts at $0.100 per million input tokens and $0.200 per million output tokens via Poolside. Reused prompt prefixes cost $0.0100 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
| $0.100 | $0.0100 | $0.200 | 1.0M/— | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Laguna S 2.1 model size
Laguna S 2.1 has 118 billion parameters. See how it compares to other models in the same parameter range.
Laguna S 2.1 context window
Input and output token limits for Laguna S 2.1, plus how it ranks on long-context understanding.
Laguna S 2.1 API
Available from the model provider
Laguna S 2.1 is available from Poolside. It is not currently routed through the LLM Stats gateway.
Read the official API documentationLaguna S 2.1 latency
Laguna S 2.1 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Laguna S 2.1 examples
Recent arena outputs from Laguna S 2.1, picked from the highest-ranked matchups.
Laguna S 2.1 license
Laguna S 2.1 is released under the OpenMDW License v1.1 license, which permits commercial use, has 118.0B parameters.
- License
- OpenMDW License v1.1
- Commercial use allowed
- Parameters
- 118.0B
Open Model, Data and Weights (OpenMDW) License Agreement, version 1.1 - permits commercial and non-commercial use.
Laguna S 2.1 resources
Official sources for Laguna S 2.1: api documentation, official playground, official launch post, model weights.
Laguna S 2.1 vs other models
The most-compared alternatives to Laguna S 2.1 are Gemini 3 Flash, Qwen3.7 Max, Kimi K2.6. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Laguna S 2.1
Models ranked just above and below Laguna S 2.1 by LLM Stats score.
FAQ
Common questions about Laguna S 2.1.