Minimax Models

33 modelsGeneral models free to startUp to 1M context

Usage

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

Tokens

51.3B

Requests

536K

Models in use

30 of 33

Tokens per day, stacked by model

02.2B4.5B10-2210-2911-0511-1211-192026-10-22 — 2,167,344,420 tokens minimax-m3.1-flash: 1,769,039,450 minimax-m3: 128,685,570 coding-minimax-m2.7-highspeed: 92,272,190 14 more models: 68,774,290 cc-minimax-m2.7: 53,384,850 coding-minimax-m3-free: 34,659,485 cc-minimax-m3: 14,543,605 coding-minimax-m3: 5,984,9802026-10-23 — 1,373,717,765 tokens coding-minimax-m3: 597,969,625 minimax-m3.1-flash: 575,782,320 coding-minimax-m2.7-highspeed: 57,171,980 coding-minimax-m3-free: 48,200,780 14 more models: 47,655,650 cc-minimax-m2.7: 39,436,915 minimax-m3: 6,846,860 cc-minimax-m3: 649,385 coding-minimax-m2.7: 4,2502026-10-24 — 4,496,882,005 tokens coding-minimax-m3: 3,472,196,170 minimax-m3.1-flash: 740,451,420 14 more models: 91,518,040 coding-minimax-m3-free: 63,390,045 coding-minimax-m2.7-highspeed: 50,381,745 cc-minimax-m2.7: 49,366,480 minimax-m3: 27,905,480 cc-minimax-m3: 1,672,6252026-10-25 — 3,827,481,830 tokens coding-minimax-m3: 3,081,502,830 minimax-m3.1-flash: 564,059,880 cc-minimax-m2.7: 56,940,050 coding-minimax-m3-free: 49,463,585 14 more models: 37,796,340 coding-minimax-m2.7-highspeed: 25,619,650 minimax-m3: 12,099,4952026-10-26 — 1,424,379,450 tokens coding-minimax-m3: 1,190,787,315 coding-minimax-m3-free: 60,481,440 coding-minimax-m2.7-highspeed: 56,084,755 minimax-m3.1-flash: 46,967,710 cc-minimax-m2.7: 31,204,765 14 more models: 31,152,040 minimax-m3: 7,680,640 coding-minimax-m2.7: 14,260 cc-minimax-m3: 6,5252026-10-27 — 1,029,265,175 tokens minimax-m3.1-flash: 532,097,080 coding-minimax-m3: 242,728,830 minimax-m3: 110,199,610 coding-minimax-m3-free: 59,462,810 coding-minimax-m2.7-highspeed: 37,543,230 14 more models: 30,210,865 cc-minimax-m2.7: 9,388,315 cc-minimax-m3: 7,620,350 coding-minimax-m2.7: 14,0852026-10-28 — 1,846,781,530 tokens coding-minimax-m3: 1,054,194,680 minimax-m3.1-flash: 359,782,685 minimax-m3: 146,569,390 coding-minimax-m3-free: 103,617,225 coding-minimax-m2.7-highspeed: 72,478,505 cc-minimax-m2.7: 59,703,655 14 more models: 39,375,350 cc-minimax-m3: 11,057,870 coding-minimax-m2.7: 2,1702026-10-29 — 3,583,847,170 tokens coding-minimax-m3: 2,309,796,685 minimax-m3.1-flash: 909,723,335 minimax-m3: 110,431,385 coding-minimax-m2.7: 95,188,945 coding-minimax-m2.7-highspeed: 59,424,655 coding-minimax-m3-free: 52,511,040 14 more models: 25,355,730 cc-minimax-m2.7: 21,278,300 cc-minimax-m3: 137,0952026-10-30 — 2,311,603,165 tokens coding-minimax-m3: 1,508,767,715 coding-minimax-m2.7: 387,629,390 minimax-m3.1-flash: 150,450,325 coding-minimax-m3-free: 90,150,320 cc-minimax-m3: 54,930,955 cc-minimax-m2.7: 36,922,725 coding-minimax-m2.7-highspeed: 35,181,455 minimax-m3: 28,170,795 14 more models: 19,399,4852026-10-31 — 819,222,115 tokens coding-minimax-m3: 570,125,590 coding-minimax-m3-free: 70,902,490 coding-minimax-m2.7-highspeed: 49,393,555 minimax-m3.1-flash: 46,227,580 cc-minimax-m2.7: 37,765,595 14 more models: 25,905,000 minimax-m3: 14,132,850 cc-minimax-m3: 4,769,4552026-11-01 — 2,564,734,935 tokens coding-minimax-m3: 1,674,771,555 minimax-m3.1-flash: 379,278,040 minimax-m3: 326,324,620 coding-minimax-m2.7-highspeed: 74,359,510 14 more models: 47,825,640 cc-minimax-m2.7: 40,318,390 coding-minimax-m3-free: 19,737,315 coding-minimax-m2.7: 2,119,8652026-11-02 — 4,308,396,005 tokens coding-minimax-m3: 2,375,734,765 minimax-m3.1-flash: 1,282,895,755 coding-minimax-m2.7-highspeed: 499,959,930 minimax-m3: 48,299,840 14 more models: 40,099,080 cc-minimax-m2.7: 34,104,335 coding-minimax-m3-free: 27,292,035 cc-minimax-m3: 5,795 coding-minimax-m2.7: 4,4702026-11-03 — 1,728,071,060 tokens minimax-m3.1-flash: 867,505,710 coding-minimax-m3: 351,180,860 coding-minimax-m2.7-highspeed: 308,785,970 cc-minimax-m2.7: 89,324,490 14 more models: 57,446,045 coding-minimax-m3-free: 37,081,770 minimax-m3: 16,143,425 cc-minimax-m3: 602,7902026-11-04 — 1,321,342,690 tokens coding-minimax-m2.7-highspeed: 412,751,080 minimax-m3.1-flash: 321,385,565 cc-minimax-m2.7: 231,291,470 coding-minimax-m3: 194,331,600 minimax-m3: 76,758,710 coding-minimax-m3-free: 56,900,965 14 more models: 27,921,295 coding-minimax-m2.7: 1,070 cc-minimax-m3: 9352026-11-05 — 1,960,132,270 tokens coding-minimax-m3: 1,212,604,550 minimax-m3.1-flash: 536,949,400 minimax-m3: 64,118,020 coding-minimax-m2.7-highspeed: 45,855,540 coding-minimax-m3-free: 42,618,395 cc-minimax-m2.7: 40,735,010 14 more models: 17,234,795 cc-minimax-m3: 16,5602026-11-06 — 745,926,020 tokens minimax-m3.1-flash: 331,797,745 coding-minimax-m3: 210,433,445 coding-minimax-m2.7-highspeed: 77,620,220 minimax-m3: 58,395,010 coding-minimax-m3-free: 46,521,745 14 more models: 16,925,385 cc-minimax-m3: 4,103,545 cc-minimax-m2.7: 126,795 coding-minimax-m2.7: 2,1302026-11-07 — 1,381,685,590 tokens coding-minimax-m3: 900,082,655 minimax-m3.1-flash: 248,674,705 minimax-m3: 108,558,445 coding-minimax-m2.7-highspeed: 69,850,710 coding-minimax-m3-free: 43,819,510 14 more models: 10,485,185 cc-minimax-m2.7: 127,310 cc-minimax-m3: 84,775 coding-minimax-m2.7: 2,2952026-11-08 — 2,162,502,075 tokens coding-minimax-m3: 1,540,745,065 minimax-m3: 354,703,570 minimax-m3.1-flash: 176,537,130 coding-minimax-m2.7-highspeed: 44,032,070 coding-minimax-m3-free: 27,718,405 14 more models: 18,595,150 cc-minimax-m2.7: 164,655 cc-minimax-m3: 3,725 coding-minimax-m2.7: 2,3052026-11-09 — 2,018,637,285 tokens coding-minimax-m3: 1,491,012,590 minimax-m3.1-flash: 400,174,500 coding-minimax-m3-free: 57,961,030 minimax-m3: 25,140,200 coding-minimax-m2.7-highspeed: 22,263,545 cc-minimax-m3: 11,036,725 14 more models: 10,881,695 cc-minimax-m2.7: 159,500 coding-minimax-m2.7: 7,5002026-11-10 — 1,031,490,200 tokens minimax-m3.1-flash: 705,781,330 minimax-m3: 108,068,340 14 more models: 67,542,680 coding-minimax-m3-free: 66,733,725 cc-minimax-m3: 42,639,050 coding-minimax-m2.7-highspeed: 24,396,695 coding-minimax-m3: 16,247,880 cc-minimax-m2.7: 80,5002026-11-11 — 837,332,735 tokens minimax-m3.1-flash: 667,235,565 coding-minimax-m3-free: 66,083,395 cc-minimax-m3: 43,889,200 coding-minimax-m2.7-highspeed: 20,514,205 14 more models: 20,335,230 minimax-m3: 13,900,675 coding-minimax-m3: 5,229,415 cc-minimax-m2.7: 141,335 coding-minimax-m2.7: 3,7152026-11-12 — 1,028,054,255 tokens minimax-m3.1-flash: 501,477,280 coding-minimax-m3: 359,640,910 coding-minimax-m2.7-highspeed: 59,022,465 coding-minimax-m3-free: 58,229,700 minimax-m3: 28,525,620 14 more models: 20,732,250 cc-minimax-m3: 273,230 cc-minimax-m2.7: 152,8002026-11-13 — 724,389,395 tokens minimax-m3.1-flash: 312,631,780 coding-minimax-m3: 244,632,185 coding-minimax-m2.7-highspeed: 66,443,660 coding-minimax-m3-free: 46,155,090 14 more models: 34,600,300 minimax-m3: 18,804,635 cc-minimax-m3: 754,610 cc-minimax-m2.7: 366,095 coding-minimax-m2.7: 1,0402026-11-14 — 1,272,702,145 tokens minimax-m3.1-flash: 703,362,630 coding-minimax-m3: 277,246,710 14 more models: 99,027,265 cc-minimax-m3: 92,206,790 coding-minimax-m3-free: 67,010,465 coding-minimax-m2.7-highspeed: 25,239,865 minimax-m3: 8,452,370 cc-minimax-m2.7: 156,0502026-11-15 — 1,205,232,305 tokens minimax-m3.1-flash: 614,579,995 minimax-m3: 280,776,110 cc-minimax-m3: 183,467,195 coding-minimax-m3-free: 70,265,965 coding-minimax-m2.7-highspeed: 28,117,890 14 more models: 26,501,200 coding-minimax-m3: 1,360,525 cc-minimax-m2.7: 161,300 coding-minimax-m2.7: 2,1252026-11-16 — 289,035,875 tokens minimax-m3.1-flash: 95,888,120 minimax-m3: 59,403,250 coding-minimax-m3-free: 50,095,505 14 more models: 47,093,375 coding-minimax-m2.7-highspeed: 35,794,150 coding-minimax-m3: 604,355 cc-minimax-m2.7: 156,085 coding-minimax-m2.7: 1,0352026-11-17 — 1,164,641,395 tokens minimax-m3.1-flash: 869,712,830 coding-minimax-m3: 117,470,960 coding-minimax-m2.7-highspeed: 65,714,020 coding-minimax-m3-free: 57,544,160 minimax-m3: 36,570,340 14 more models: 17,458,170 cc-minimax-m2.7: 165,800 coding-minimax-m2.7: 3,335 cc-minimax-m3: 1,7802026-11-18 — 807,213,860 tokens minimax-m3.1-flash: 638,393,960 coding-minimax-m3-free: 48,043,590 coding-minimax-m2.7-highspeed: 46,038,525 coding-minimax-m2.7: 24,004,105 14 more models: 20,679,415 cc-minimax-m3: 14,132,885 minimax-m3: 13,065,870 coding-minimax-m3: 2,685,805 cc-minimax-m2.7: 169,7052026-11-19 — 1,874,236,990 tokens minimax-m3.1-flash: 1,473,353,310 minimax-m3: 118,189,185 coding-minimax-m3: 91,454,155 coding-minimax-m3-free: 70,855,890 coding-minimax-m2.7-highspeed: 49,401,010 14 more models: 40,528,990 cc-minimax-m3: 26,805,680 coding-minimax-m2.7: 3,476,950 cc-minimax-m2.7: 171,820
  • coding-minimax-m3
  • minimax-m3.1-flash
  • coding-minimax-m2.7-highspeed
  • minimax-m3
  • coding-minimax-m3-free
  • cc-minimax-m2.7
  • cc-minimax-m3
  • coding-minimax-m2.7
  • 14 more models

Which models that traffic went to

  1. Coding MiniMax M348.9%25.1B
  2. MiniMax M3.1 Flash32.8%16.8B
  3. Coding MiniMax M2.7 Highspeed4.9%2.5B
  4. MiniMax M34.6%2.4B
  5. Coding MiniMax M3 (free)3.1%1.6B
  6. CC MiniMax M2.71.6%833M
  7. CC MiniMax M31.0%515M
  8. Coding MiniMax M2.71.0%512M
  9. 14 more models2.1%1.1B

Share of 51.3B tokens. 8 models with traffic report no token counts and cannot be ranked here, including minimax-h3-max and coding-minimax-m2.1-free — 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 33 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 33 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
coding-minimax-m3-freeTakes text, vision, video, returns text.1M524KFreeFree/M—74 tok/s1.67 s
cc-minimax-m3Takes text, vision, video, returns text.1M524K$0.1$0.1/M—59 tok/s1.77 s
MiniMax-Text-01Takes text, returns text.1M—$0.14$1.12/M—29 tok/s1.54 s
minimax-m3.1-flashTakes text, vision, video, returns text.1M524K$0.165$0.66/M$0.0165/M87 tok/s2.10 s
coding-minimax-m3Takes text, vision, video, returns text.1M524K$0.2$0.2/M—106 tok/s1.30 s
minimax-m3Takes text, vision, video, returns text.1M524K$0.288$1.152/M—82 tok/s1.37 s
coding-minimax-m2-freeTakes text, returns text.205K—FreeFree/M—70 tok/s0.92 s
coding-minimax-m2.1-freeTakes text, returns text.205K—FreeFree/M—43 tok/s1.40 s
coding-minimax-m2.5-freeTakes text, returns text.205K—FreeFree/M—70 tok/s0.68 s
coding-minimax-m2.7-freeTakes text, returns text.205K—FreeFree/M—83 tok/s1.13 s
minimax-m2.7-freeTakes text, returns text.205K—FreeFree/M———
cc-minimax-m2.1Takes text, returns text.205K—$0.1$0.1/M—39 tok/s0.51 s
cc-minimax-m2.5Takes text, returns text.205K—$0.1$0.1/M—180 tok/s1.80 s
cc-minimax-m2.5-highspeedTakes text, returns text.205K—$0.1$0.1/M—36 tok/s0.68 s
cc-minimax-m2.7Takes text, returns text.205K—$0.1$0.1/M—7 tok/s0.69 s
cc-minimax-m2.7-highspeedTakes text, returns text.205K—$0.1$0.1/M—40 tok/s2.72 s
mm-minimax-m2.7-highspeedTakes text, returns text.205K—$0.1$0.1/M—50 tok/s1.43 s
coding-minimax-m2Takes text, returns text.205K—$0.2$0.2/M—46 tok/s2.10 s
coding-minimax-m2.1Takes text, returns text.205K—$0.2$0.2/M—79 tok/s0.53 s
coding-minimax-m2.5Takes text, returns text.205K—$0.2$0.2/M—80 tok/s1.04 s
coding-minimax-m2.5-highspeedTakes text, returns text.205K—$0.2$0.2/M—82 tok/s1.33 s
coding-minimax-m2.7Takes text, returns text.205K—$0.2$0.2/M—63 tok/s1.19 s
coding-minimax-m2.7-highspeedTakes text, returns text.205K—$0.2$0.2/M—18 tok/s4.28 s
minimax-m2.1Takes text, returns text.205K—$0.288$1.152/M———
minimax-m2.5Takes text, returns text.205K—$0.288$1.152/M—39 tok/s9.23 s
minimax-m2.5-highspeedTakes text, returns text.205K—$0.288$1.152/M———
minimax-m2.7Takes text, returns text.205K—$0.2958$1.1832/M$0.0592/M32 tok/s1.95 s
cc-MiniMax-M2Takes text, returns text.——$0.1$0.1/M—8 tok/s0.92 s
cc-minimax-m2Takes text, returns text.——$0.1$0.1/M—8 tok/s0.92 s
alicloud-minimax-m2.5Takes , returns text.——$0.2876$1.1504/M$0.0575/M73 tok/s1.44 s
MiniMaxAI/MiniMax-M1-80kTakes , returns text.——$0.6$2.4/M———
minimax-h3Takes text, vision, audio, video, returns video.——from $0.0774 / s———
minimax-h3-maxTakes text, vision, returns video.——from $0.0511 / s———

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.

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 coding-minimax-m3-free for long-form reasoning.

Which of these models reason before answering?

18 of the 33 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 minimax-m3.1-flash bills cache hits at 10% of the input rate and alicloud-minimax-m2.5 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.

Start calling Minimax in one line

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