AIHubMixAIHubMix

Flux Models

5 modelsGeneral models free to start

Usage

Last 29 days · 2026-07-22 to 2026-08-20

Tokens

20.7M

Requests

631

Models in use

4 of 5

Tokens per day, stacked by model

01.4M2.9M07-2207-2908-0608-1308-202026-07-22 — 1,769,030 tokens flux-2-pro: 969,030 FLUX-1.1-pro: 800,0002026-07-23 — 1,433,555 tokens flux-2-pro: 833,555 FLUX-1.1-pro: 600,0002026-07-24 — 739,800 tokens flux-2-pro: 739,8002026-07-25 — 1,211,030 tokens flux-2-pro: 1,211,0302026-07-26 — 150,000 tokens flux-2-pro: 150,0002026-07-27 — 1,016,060 tokens flux-2-flex: 1,016,0602026-07-28 — 0 tokens2026-07-29 — 2,896,120 tokens flux-2-pro: 2,271,840 flux-2-flex: 524,280 FLUX-1.1-pro: 100,0002026-07-30 — 1,181,345 tokens flux-2-pro: 1,181,3452026-07-31 — 0 tokens2026-08-01 — 78,640 tokens flux-2-pro: 78,6402026-08-03 — 1,222,060 tokens flux-2-pro: 922,060 FLUX-1.1-pro: 300,0002026-08-04 — 545,185 tokens flux-2-pro: 545,1852026-08-05 — 466,545 tokens flux-2-pro: 466,5452026-08-06 — 466,545 tokens flux-2-pro: 466,5452026-08-07 — 466,545 tokens flux-2-pro: 466,5452026-08-08 — 466,545 tokens flux-2-pro: 466,5452026-08-09 — 616,545 tokens flux-2-pro: 616,5452026-08-10 — 466,545 tokens flux-2-pro: 466,5452026-08-11 — 766,545 tokens flux-2-pro: 766,5452026-08-12 — 466,545 tokens flux-2-pro: 466,5452026-08-13 — 833,535 tokens flux-2-pro: 702,465 flux-2-flex: 131,0702026-08-14 — 466,545 tokens flux-2-pro: 466,5452026-08-15 — 466,545 tokens flux-2-pro: 466,5452026-08-16 — 466,545 tokens flux-2-pro: 466,5452026-08-17 — 311,030 tokens flux-2-pro: 311,0302026-08-18 — 311,030 tokens flux-2-pro: 311,0302026-08-19 — 611,030 tokens flux-2-pro: 461,030 flux-2-flex: 150,0002026-08-20 — 766,545 tokens flux-2-pro: 766,545
  • flux-2-pro
  • flux-2-flex
  • FLUX-1.1-pro

Which models that traffic went to

  1. Flux 2 Pro82.5%17M
  2. Flux 2 Flex8.8%1.8M
  3. FLUX-1.1-pro8.7%1.8M

Share of 20.7M tokens. 1 models with traffic report no token counts and cannot be ranked here, including flux-kontext-max — they are in the request view.

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 5 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 5 Flux Models

Open in model list
Flux 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
FLUX-1.1-proTakes text, vision, returns vision.FreeFree/M
flux-2-flexTakes text, vision, returns vision.FreeFree/M
flux-2-proTakes text, vision, returns vision.FreeFree/M
flux-kontext-maxFreeFree/M
fx-flux-2-pro$2.00$2.00/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.

Flux on AIHubMix

Which Flux model should I start with?

FLUX-1.1-pro is free on input — the cheapest entry here that declares a token price. Move up to fx-flux-2-pro 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 Flux 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
141 modelsOpenAI
133 modelsGoogle
83 modelsZ.AI
66 modelsLlama
52 models

Start calling Flux in one line

One key, one endpoint, 859 models across 37 model authors.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect