Liquid Models

2 modelsGeneral models free to startUp to 131K contextOfficial site ↗

Usage

Last 29 days · 2026-10-22 to 2026-11-19

Tokens

10M

Requests

1.7K

Models in use

2 of 2

Tokens per day, stacked by model

01.2M2.4M10-2210-2911-0511-1211-192026-10-22 — 448,485 tokens lfm-2.5-2.6b-free: 448,4852026-10-23 — 412,995 tokens lfm-2.5-2.6b-free: 412,9952026-10-24 — 203,835 tokens lfm-2.5-2.6b-free: 203,8352026-10-25 — 301,895 tokens lfm-2.5-2.6b-free: 301,8952026-10-26 — 944,350 tokens lfm-2.5-2.6b-free: 944,3502026-10-27 — 201,415 tokens lfm-2.5-2.6b-free: 201,4152026-10-28 — 6,660 tokens lfm-2.5-2.6b-free: 6,6602026-10-29 — 562,765 tokens lfm-2.5-2.6b-free: 562,7652026-10-30 — 85,235 tokens lfm-2.5-2.6b-free: 85,2352026-10-31 — 28,730 tokens lfm-2.5-2.6b-free: 28,7302026-11-01 — 204,480 tokens lfm-2.5-2.6b-free: 204,4802026-11-02 — 81,005 tokens lfm-2.5-2.6b-free: 81,0052026-11-03 — 40,780 tokens lfm-2.5-2.6b-free: 40,7802026-11-04 — 77,805 tokens lfm-2.5-2.6b-free: 77,8052026-11-05 — 318,185 tokens lfm-2.5-2.6b-free: 318,1852026-11-06 — 6,870 tokens lfm-2.5-2.6b-free: 6,8702026-11-07 — 175,865 tokens lfm-2.5-2.6b-free: 175,8652026-11-08 — 44,055 tokens lfm-2.5-2.6b-free: 44,0552026-11-09 — 399,915 tokens lfm-2.5-2.6b-free: 399,9152026-11-10 — 287,950 tokens lfm-2.5-2.6b-free: 287,9502026-11-11 — 2,366,265 tokens lfm-2.5-2.6b-free: 2,366,2652026-11-12 — 205,500 tokens lfm-2.5-2.6b-free: 205,5002026-11-13 — 442,350 tokens lfm-3-1.7b-free: 270,450 lfm-2.5-2.6b-free: 171,9002026-11-14 — 195,995 tokens lfm-3-1.7b-free: 195,9952026-11-15 — 453,490 tokens lfm-3-1.7b-free: 453,4902026-11-16 — 181,900 tokens lfm-3-1.7b-free: 181,9002026-11-17 — 116,705 tokens lfm-3-1.7b-free: 116,7052026-11-18 — 1,201,250 tokens lfm-3-1.7b-free: 1,201,2502026-11-19 — 31,745 tokens lfm-3-1.7b-free: 31,745
  • lfm-2.5-2.6b-free
  • lfm-3-1.7b-free

Which models that traffic went to

  1. Lfm 2.5 2.6b (free)75.6%7.6M
  2. Lfm 3 1.7b (free)24.4%2.5M

Share of 10M 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 29 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 Liquid Models

Open in model list
Liquid 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
lfm-2.5-2.6b-freeTakes text, returns text.131KFreeFree/M
lfm-3-1.7b-freeTakes text, returns text.—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.

Liquid on AIHubMix

Which Liquid model should I start with?

lfm-2.5-2.6b-free is free on input — the cheapest entry here that declares a token price, and it carries a 131K context. Move up to lfm-3-1.7b-free when answer quality matters more than cost.

Which of these models reason before answering?

1 of the 2 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.

Do I need a separate Liquid 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 Liquid in one line

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