AIHubMixAIHubMix

InclusionAI Models

7 modelsGeneral models free to startUp to 262K context

Usage

Last 23 days · 2026-07-15 to 2026-08-11

Tokens

2.8B

Requests

16.3K

Models in use

7 of 7

Tokens per day

0479M958M07-1507-2708-0308-102026-07-15 — 2,670 tokens2026-07-16 — 1,935 tokens2026-07-17 — 1,085 tokens2026-07-19 — 330,945 tokens2026-07-20 — 0 tokens2026-07-21 — 0 tokens2026-07-26 — 21,634,075 tokens2026-07-27 — 771,286,860 tokens2026-07-28 — 177,904,050 tokens2026-07-29 — 11,403,060 tokens2026-07-30 — 958,419,395 tokens2026-07-31 — 4,378,240 tokens2026-08-01 — 471,012,785 tokens2026-08-02 — 371,117,075 tokens2026-08-03 — 7,475,870 tokens2026-08-04 — 13,574,230 tokens2026-08-05 — 17,802,425 tokens2026-08-06 — 7,325,835 tokens2026-08-07 — 435 tokens2026-08-08 — 2,670 tokens2026-08-09 — 0 tokens2026-08-10 — 645 tokens2026-08-11 — 29,245 tokens

Which models that traffic went to

  1. ling-3.0-flash-free100.0%2.8B
  2. inclusionAI/Ling-flash-2.0<0.1%193K
  3. inclusionAI/Ling-mini-2.0<0.1%163K
  4. ling-3.0-tiny-free<0.1%29.2K

Share of 2.8B tokens. 3 models with traffic report no token counts and cannot be ranked here, including inclusionAI/Ling-1T and inclusionAI/Ring-flash-2.0 — 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 23 days, counting the 7 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 7 InclusionAI Models

Open in model list
InclusionAI 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
ling-3.0-flash-freeTakes text, returns text.262KFreeFree/M
ling-3.0-tiny-freeTakes text, returns text.262KFreeFree/M
inclusionAI/Ling-mini-2.0Takes text, returns text.128K$0.07$0.27/M
inclusionAI/Ling-flash-2.0Takes text, returns text.128K$0.14$0.54/M
inclusionAI/Ring-flash-2.0Takes text, returns text.128K$0.14$0.54/M
inclusionAI/Ling-1TTakes text, returns text.128K$0.55$2.19/M
inclusionAI/Ring-1TTakes text, returns text.128K$0.55$2.19/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

inclusionAI/Ling-1T vs inclusionAI/Ling-flash-2.0inclusionAI/Ling-1T vs inclusionAI/Ling-mini-2.0inclusionAI/Ling-1T vs inclusionAI/Ring-1TinclusionAI/Ling-1T vs qwen3.8-max-previewinclusionAI/Ling-1T vs kimi-k3

InclusionAI on AIHubMix

Which InclusionAI model should I start with?

ling-3.0-flash-free is free on input — the cheapest entry here that declares tool calling, and it carries a 262K context. Move up to inclusionAI/Ling-1T when answer quality matters more than cost, or to ling-3.0-tiny-free for long-form reasoning.

Which of these models reason before answering?

4 of the 7 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-), some are the open-weight repository form (inclusionAI/…), 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 InclusionAI 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 Providers

Qwen
140 modelsOpenAI
132 modelsGoogle
81 modelsZ.AI
64 modelsLlama
52 models

Start calling InclusionAI in one line

One key, one endpoint, 844 models across 35 providers.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect