AIHubMixAIHubMix

Minimax Models

31 modelsGeneral models free to startUp to 1M context

Usage

Last 30 days · 2026-07-13 to 2026-08-11

Tokens

26.7B

Requests

754K

Models in use

30 of 31

Tokens per day

01.2B2.4B07-1307-2007-2708-0308-102026-07-13 — 1,936,503,840 tokens2026-07-14 — 1,436,654,760 tokens2026-07-15 — 1,128,663,850 tokens2026-07-16 — 1,440,833,010 tokens2026-07-17 — 1,959,316,920 tokens2026-07-18 — 175,276,320 tokens2026-07-19 — 328,140,100 tokens2026-07-20 — 1,077,789,335 tokens2026-07-21 — 1,056,750,760 tokens2026-07-22 — 345,704,505 tokens2026-07-23 — 766,787,680 tokens2026-07-24 — 1,013,905,740 tokens2026-07-25 — 731,009,395 tokens2026-07-26 — 916,591,315 tokens2026-07-27 — 640,790,980 tokens2026-07-28 — 686,069,845 tokens2026-07-29 — 579,962,015 tokens2026-07-30 — 963,271,545 tokens2026-07-31 — 1,256,661,820 tokens2026-08-01 — 248,197,350 tokens2026-08-02 — 583,771,005 tokens2026-08-03 — 348,049,770 tokens2026-08-04 — 354,277,595 tokens2026-08-05 — 382,900,155 tokens2026-08-06 — 913,050,835 tokens2026-08-07 — 1,329,841,105 tokens2026-08-08 — 2,402,292,235 tokens2026-08-09 — 844,735,710 tokens2026-08-10 — 579,296,630 tokens2026-08-11 — 308,182,575 tokens

Which models that traffic went to

  1. minimax-m338.2%10.2B
  2. cc-minimax-m321.4%5.7B
  3. cc-minimax-m2.711.3%3B
  4. coding-minimax-m39.6%2.6B
  5. coding-minimax-m3-free7.7%2.1B
  6. coding-minimax-m2.7-highspeed5.1%1.4B
  7. minimax-m2.72.0%536M
  8. cc-minimax-m2.7-highspeed1.3%357M
  9. 21 more models3.4%914M

Share of 26.7B tokens. 1 models with traffic report no token counts and cannot be ranked here, including MiniMaxAI/MiniMax-M1-80k — 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 30 days, counting the 31 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 31 Minimax Models

Open in model list
Minimax 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
MiniMax-Text-01Takes text. Output modality not published.1M—$0.14$1.12/M—29 tok/s1.54 s
minimax-m3Takes text, returns text.1M192K$0.29$1.15/M—42 tok/s1.12 s
coding-minimax-m2-freeTakes text, returns text.205K13KFreeFree/M———
coding-minimax-m2.1-freeTakes text, returns text.205K13KFreeFree/M———
coding-minimax-m2.5-freeTakes text, returns text.205K13KFreeFree/M———
coding-minimax-m2.7-freeTakes text, returns text.205K13KFreeFree/M———
coding-minimax-m3-freeTakes text, returns text.205K13KFreeFree/M———
coding-minimax-m2Takes text, returns text.205K13K$0.20$0.20/M———
coding-minimax-m2.1Takes text, returns text.205K13K$0.20$0.20/M———
coding-minimax-m2.5Takes text, returns text.205K13K$0.20$0.20/M———
coding-minimax-m2.5-highspeedTakes text, returns text.205K13K$0.20$0.20/M———
coding-minimax-m2.7Takes text, returns text.205K13K$0.20$0.20/M———
coding-minimax-m2.7-highspeedTakes text, returns text.205K13K$0.20$0.20/M———
coding-minimax-m3Takes text, returns text.205K13K$0.20$0.20/M———
minimax-m2Takes text, returns text.205K192K$0.29$1.15/M—65 tok/s1.41 s
minimax-m2.1Takes text, returns text.205K192K$0.29$1.15/M—35 tok/s0.79 s
minimax-m2.5Takes text, returns text.205K192K$0.29$1.15/M—27 tok/s1.49 s
minimax-m2.5-highspeedTakes text, returns text.205K192K$0.29$1.15/M—29 tok/s1.35 s
minimax-m2.7Takes text, returns text.200K128K$0.30$1.18/M$0.06/M34 tok/s4.89 s
minimax-h3Takes text, vision, audio, video, returns video.——FreeFree/M———
cc-MiniMax-M2Takes text, returns text.——$0.10$0.10/M———
cc-minimax-m2Takes text, returns text.——$0.10$0.10/M———
cc-minimax-m2.1Takes text, returns text.——$0.10$0.10/M———
cc-minimax-m2.5Takes text, returns text.——$0.10$0.10/M———
cc-minimax-m2.5-highspeedTakes text, returns text.——$0.10$0.10/M———
cc-minimax-m2.7Takes text, returns text.——$0.10$0.10/M———
cc-minimax-m2.7-highspeedTakes text, returns text.——$0.10$0.10/M———
cc-minimax-m3Takes text, returns text.——$0.10$0.10/M———
mm-minimax-m2.7-highspeedTakes text, returns text.——$0.10$0.10/M———
alicloud-minimax-m2.5——$0.29$1.15/M$0.06/M——
MiniMaxAI/MiniMax-M1-80k——$0.60$2.40/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

cc-MiniMax-M2 vs cc-minimax-m2cc-MiniMax-M2 vs cc-minimax-m2.1cc-MiniMax-M2 vs cc-minimax-m2.5cc-MiniMax-M2 vs qwen3.8-max-previewcc-MiniMax-M2 vs kimi-k3

Minimax on AIHubMix

Which Minimax model should I start with?

coding-minimax-m2-free is free on input — the cheapest entry here that declares tool calling, and it carries a 205K context. Move up to MiniMaxAI/MiniMax-M1-80k when answer quality matters more than cost, or to minimax-m3 for long-form reasoning.

Which of these models reason before answering?

18 of the 31 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 (MiniMaxAI/…), 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 alicloud-minimax-m2.5 bills cache hits at 20% of the input rate and minimax-m2.7 bills cache hits at 20% 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 Minimax 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 Minimax 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