Poolside Models

2 modelsGeneral models free to startUp to 1.05M context

Usage

Last 20 days · 2026-08-18 to 2026-09-16

Tokens

82.8M

Requests

1K

Models in use

2 of 2

Tokens per day, stacked by model

06.4M12.7M08-1808-2509-112026-08-18 — 133,670 tokens laguna-xs-2.1-free: 70,225 laguna-s-2.1-free: 63,4452026-08-19 — 125,535 tokens laguna-s-2.1-free: 122,380 laguna-xs-2.1-free: 3,1552026-08-20 — 44,230 tokens laguna-s-2.1-free: 41,540 laguna-xs-2.1-free: 2,6902026-08-21 — 1,341,685 tokens laguna-s-2.1-free: 1,340,270 laguna-xs-2.1-free: 1,4152026-08-22 — 7,795,260 tokens laguna-s-2.1-free: 7,731,390 laguna-xs-2.1-free: 63,8702026-08-23 — 5,203,480 tokens laguna-xs-2.1-free: 5,032,315 laguna-s-2.1-free: 171,1652026-08-24 — 5,511,090 tokens laguna-s-2.1-free: 5,118,935 laguna-xs-2.1-free: 392,1552026-08-25 — 4,127,300 tokens laguna-xs-2.1-free: 2,525,510 laguna-s-2.1-free: 1,601,7902026-08-26 — 1,302,610 tokens laguna-s-2.1-free: 1,291,815 laguna-xs-2.1-free: 10,7952026-08-27 — 1,803,595 tokens laguna-s-2.1-free: 1,794,840 laguna-xs-2.1-free: 8,7552026-08-28 — 676,790 tokens laguna-s-2.1-free: 675,135 laguna-xs-2.1-free: 1,6552026-09-08 — 0 tokens2026-09-09 — 1,170 tokens laguna-xs-2.1-free: 630 laguna-s-2.1-free: 5402026-09-10 — 1,449,370 tokens laguna-xs-2.1-free: 1,434,190 laguna-s-2.1-free: 15,1802026-09-11 — 5,751,250 tokens laguna-xs-2.1-free: 5,020,620 laguna-s-2.1-free: 730,6302026-09-12 — 7,898,570 tokens laguna-s-2.1-free: 6,402,120 laguna-xs-2.1-free: 1,496,4502026-09-13 — 11,522,345 tokens laguna-s-2.1-free: 9,261,195 laguna-xs-2.1-free: 2,261,1502026-09-14 — 4,615,640 tokens laguna-s-2.1-free: 2,891,915 laguna-xs-2.1-free: 1,723,7252026-09-15 — 12,718,695 tokens laguna-xs-2.1-free: 6,456,370 laguna-s-2.1-free: 6,262,3252026-09-16 — 10,744,760 tokens laguna-xs-2.1-free: 9,732,220 laguna-s-2.1-free: 1,012,540
  • laguna-s-2.1-free
  • laguna-xs-2.1-free

Which models that traffic went to

  1. Laguna S 2.1 (free)56.2%46.5M
  2. Laguna Xs 2.1 (free)43.8%36.2M

Share of 82.8M tokens.

The two views disagree on purpose: a model can take a large share of the calls and a small share of the tokens — many short requests — or the reverse. Which one matters depends on whether your cost is driven by call volume or by prompt length. Measured on AIHubMix over the last 20 days, counting the 2 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 2 Poolside Models

Open in model list
Poolside models on AIHubMix with input and output modalities, context length, maximum output, price per million tokens including cache read and cache write rates, and measured throughput and latency.
Modalities
laguna-s-2.1-freeTakes text, returns text.1.05M262KFreeFree/M
laguna-xs-2.1-freeTakes text, returns text.262K—FreeFree/M

Prices are USD per million tokens; cache read and cache write are the rates for prompt-cache hits and for writing a prompt into the cache. Throughput and latency are measured on AIHubMix — the same figures the model detail page shows — not vendor claims. A dash means the catalog does not publish that field for that model, which is not the same as the model not supporting it.

Common Comparisons

laguna-s-2.1-free vs laguna-xs-2.1-freelaguna-s-2.1-free vs qwen3.8-max-previewkimi-k3 vs laguna-s-2.1-freeglm-5.2 vs laguna-s-2.1-freegrok-4.5 vs laguna-s-2.1-free

Poolside on AIHubMix

Which Poolside model should I start with?

laguna-s-2.1-free is free on input — the cheapest entry here that declares tool calling, and it carries a 1.05M context. Move up to laguna-xs-2.1-free when answer quality matters more than cost.

Why are there several entries for the same model?

Because each row is a route you can call, not a model release. Some IDs name an upstream (azure-, alicloud-, cc-), and some differ only in capitalisation, kept so older integrations keep working.

The catalog does not carry a field saying which of those a given row is, so this page does not sort them into buckets it would have to invent. Every row shows that route’s own price, context and speed — compare those directly, and open a model to see the upstreams that serve it.

Do I need a separate Poolside account?

No. One AIHubMix key covers every model on this page, and switching between them is a change to the model string — billing, rate limits, and logs stay in one place.

Other Model Authors

See all model authors →
Qwen
145 modelsOpenAI
137 modelsGoogle
85 modelsZ.AI
71 modelsLlama
53 models

Start calling Poolside in one line

One key, one endpoint, 881 models across 39 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Connect

Terms & Policies