Poolside Models

4 modelsGeneral models free to startUp to 1.05M context

Usage

Last 25 days · 2026-10-22 to 2026-11-17

Tokens

22M

Requests

1.4K

Models in use

4 of 4

Tokens per day, stacked by model

06M12.1M10-2210-2911-0511-142026-10-22 — 449,735 tokens laguna-xs-2.1-free: 196,110 laguna-xs-2.1: 117,840 laguna-s-2.1: 98,220 laguna-s-2.1-free: 37,5652026-10-23 — 695,000 tokens laguna-xs-2.1-free: 445,910 laguna-s-2.1-free: 247,380 laguna-xs-2.1: 1,160 laguna-s-2.1: 5502026-10-24 — 1,734,050 tokens laguna-s-2.1: 1,577,850 laguna-xs-2.1: 142,875 laguna-s-2.1-free: 6,685 laguna-xs-2.1-free: 6,6402026-10-25 — 12,068,510 tokens laguna-s-2.1-free: 9,839,185 laguna-xs-2.1-free: 2,228,815 laguna-xs-2.1: 280 laguna-s-2.1: 2302026-10-26 — 2,027,750 tokens laguna-s-2.1-free: 2,008,075 laguna-xs-2.1-free: 9,590 laguna-xs-2.1: 7,775 laguna-s-2.1: 2,3102026-10-27 — 2,886,040 tokens laguna-s-2.1-free: 2,076,785 laguna-xs-2.1-free: 788,455 laguna-xs-2.1: 10,490 laguna-s-2.1: 10,3102026-10-28 — 750,235 tokens laguna-s-2.1-free: 725,565 laguna-xs-2.1-free: 21,610 laguna-s-2.1: 1,530 laguna-xs-2.1: 1,5302026-10-29 — 506,285 tokens laguna-s-2.1-free: 286,900 laguna-xs-2.1-free: 217,545 laguna-s-2.1: 920 laguna-xs-2.1: 9202026-10-30 — 572,285 tokens laguna-s-2.1-free: 565,905 laguna-xs-2.1-free: 4,250 laguna-s-2.1: 1,065 laguna-xs-2.1: 1,0652026-10-31 — 331,705 tokens laguna-s-2.1-free: 317,710 laguna-xs-2.1-free: 13,9952026-11-01 — 0 tokens2026-11-02 — 0 tokens2026-11-03 — 0 tokens2026-11-04 — 0 tokens2026-11-05 — 0 tokens2026-11-06 — 0 tokens2026-11-07 — 0 tokens2026-11-08 — 0 tokens2026-11-09 — 0 tokens2026-11-11 — 0 tokens2026-11-12 — 0 tokens2026-11-14 — 0 tokens2026-11-15 — 0 tokens2026-11-16 — 0 tokens2026-11-17 — 0 tokens
  • laguna-s-2.1-free
  • laguna-xs-2.1-free
  • laguna-s-2.1
  • laguna-xs-2.1

Which models that traffic went to

  1. Laguna S 2.1 (free)73.2%16.1M
  2. Laguna Xs 2.1 (free)17.9%3.9M
  3. Laguna S 2.17.7%1.7M
  4. Laguna Xs 2.11.3%284K

Share of 22M 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 25 days, counting the 4 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 4 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-s-2.1Takes text, returns text.1.05M—$0.1$0.2/M$0.01/M
laguna-xs-2.1-freeTakes text, returns text.262K—FreeFree/M—
laguna-xs-2.1Takes text, returns text.262K—$0.1$0.2/M$0.05/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.

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-s-2.1 when answer quality matters more than cost, or to laguna-xs-2.1-free for long-form reasoning.

Which of these models reason before answering?

2 of the 4 models here declare a reasoning phase — they work through the problem before producing an answer, which helps on multi-step problems at the cost of extra output tokens. Use the Reasoning filter above the table to see them. The catalog does not record anything further about how they differ, so this page does not sort them into families.

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.

How is cached input billed?

The Cache read column is the rate for input tokens served from the prompt cache — for example laguna-s-2.1 bills cache hits at 10% of the input rate and laguna-xs-2.1 bills cache hits at 50% of the input rate. Cache write is the surcharge for putting a prompt into the cache in the first place, and only a few upstreams bill it separately. A dash in either column means the catalog carries no cache rate for that model, so plan on paying the full input rate.

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.

Start calling Poolside in one line

One key, one endpoint, 984 models across 49 model authors.