Laguna XS 2.1 is a Poolside model with 262K context, $0.06 in / $0.12 out per million tokens, last verified October 2, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.
Open-weight 256K coding model with native reasoning, local checkpoints, and hosted API access.
Recorded profile verification October 2, 2026·Individual provider fields may change
Pricing tiers: Poolside route on OpenRouter $0.06/$0.12 per MTok, cache read $0.03, FP8 serving; feed reports a 40% discount with no end date. Route context 262,144, maximum completion 32,768. Launch paid prices were $0.10/$0.20, cache $0.05; launch free inference was limited. Direct Poolside API generation ranges differ, and self-hosting OpenMDW-1.1 weights has separate compute costs.
Best for
Local coding
Agentic coding
Cost-sensitive API
Watch out
Thinking is binary and enabled in the documented setup; preserve prior reasoning_content. Exact native context is 262,144. Checkpoint card warns that older poolside_v1 tool parsers can silently drop calls without a newline; use a vLLM build containing #47311 or the documented glm47 workaround. Vendor benchmarks use pool/Harbor with patched task images and different attempt counts by benchmark; neither launch XS.2 scores nor other provider effort menus transfer. Redistribution requires retaining the OpenMDW agreement and notices.
Source receipts
Catalog figures for this model were checked against the following sources.
Answered from the verified figures on this page rather than general guidance.
How much does Laguna XS 2.1 cost per million tokens?
Laguna XS 2.1 lists base rates of $0.06 per million input tokens and $0.12 per million output tokens. Estimate both input and output token volume and any additional charges for your workload. Poolside route on OpenRouter $0.06/$0.12 per MTok, cache read $0.03, FP8 serving; feed reports a 40% discount with no end date. Route context 262,144, maximum completion 32,768. Launch paid prices were $0.10/$0.20, cache $0.05; launch free inference was limited. Direct Poolside API generation ranges differ, and self-hosting OpenMDW-1.1 weights has separate compute costs.
What is Laguna XS 2.1's context window?
Laguna XS 2.1 accepts about 262K tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Laguna XS 2.1 best for?
Laguna XS 2.1 is a budget tier from Poolside. It suits local coding, agentic coding, cost-sensitive api. Thinking is binary and enabled in the documented setup; preserve prior reasoning_content. Exact native context is 262,144. Checkpoint card warns that older poolside_v1 tool parsers can silently drop calls without a newline; use a vLLM build containing #47311 or the documented glm47 workaround. Vendor benchmarks use pool/Harbor with patched task images and different attempt counts by benchmark; neither launch XS.2 scores nor other provider effort menus transfer. Redistribution requires retaining the OpenMDW agreement and notices.
Can I self-host Laguna XS 2.1?
Laguna XS 2.1 publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.
