Qwen Models

156 modelsGeneral models from $0.0206/M inputUp to 1.05M context

Usage

Last 30 days · 2026-10-23 to 2026-11-21

Tokens

97.9B

Requests

4.9M

Models in use

135 of 156

Tokens per day, stacked by model

04B8B10-2310-3011-0611-1311-202026-10-23 — 4,628,133,845 tokens qwen3.8-max: 1,614,917,365 qwen3.7-flash: 1,062,414,945 51 more models: 913,906,625 qwen3.8-flash: 573,717,070 qwen3.8-max-2026-09-02: 350,367,505 qwen3.6-35b-a3b: 78,866,610 qwen3.7-plus: 31,471,550 qwen3-vl-plus: 2,472,1752026-10-24 — 3,208,310,730 tokens qwen3.7-flash: 1,329,084,995 qwen3.8-max: 1,058,198,455 51 more models: 400,546,635 qwen3.8-flash: 381,022,830 qwen3.8-max-2026-09-02: 32,920,655 qwen3.7-plus: 3,505,745 qwen3-vl-plus: 3,014,045 qwen3.6-35b-a3b: 17,3702026-10-25 — 4,938,822,005 tokens qwen3.7-flash: 2,088,296,585 qwen3.8-flash: 1,759,604,080 qwen3.8-max: 780,432,125 51 more models: 266,170,620 qwen3.8-max-2026-09-02: 31,352,230 qwen3.7-plus: 5,398,300 qwen3.6-35b-a3b: 4,979,030 qwen3-vl-plus: 2,589,0352026-10-26 — 3,529,473,935 tokens qwen3.7-flash: 1,954,945,295 qwen3.8-max: 689,679,645 51 more models: 587,542,315 qwen3.8-flash: 205,460,180 qwen3.6-35b-a3b: 44,487,995 qwen3.8-max-2026-09-02: 30,097,595 qwen3-vl-plus: 8,754,505 qwen3.7-plus: 8,506,4052026-10-27 — 5,694,516,490 tokens qwen3.8-flash: 3,132,538,790 qwen3.7-flash: 1,136,441,620 qwen3.8-max: 749,365,570 51 more models: 503,095,485 qwen3.6-35b-a3b: 103,098,275 qwen3.7-plus: 29,167,955 qwen3.8-max-2026-09-02: 24,482,175 qwen3-vl-plus: 16,326,6202026-10-28 — 4,109,183,645 tokens qwen3.7-flash: 1,429,676,055 qwen3.8-flash: 1,269,437,855 qwen3.8-max: 611,507,930 51 more models: 581,882,975 qwen3.7-plus: 128,904,870 qwen3.6-35b-a3b: 34,018,715 qwen3.8-max-2026-09-02: 33,978,820 qwen3-vl-plus: 19,776,4252026-10-29 — 2,457,725,920 tokens qwen3.8-flash: 1,211,007,975 qwen3.7-flash: 398,904,775 qwen3.8-max: 378,157,145 51 more models: 357,880,185 qwen3.7-plus: 66,216,860 qwen3.8-max-2026-09-02: 23,751,280 qwen3.6-35b-a3b: 12,874,650 qwen3-vl-plus: 8,933,0502026-10-30 — 1,439,174,675 tokens 51 more models: 624,966,185 qwen3.7-flash: 427,463,885 qwen3.8-flash: 250,589,550 qwen3.8-max: 108,638,075 qwen3-vl-plus: 9,614,180 qwen3.6-35b-a3b: 8,965,280 qwen3.7-plus: 7,494,405 qwen3.8-max-2026-09-02: 1,443,1152026-10-31 — 1,104,234,745 tokens 51 more models: 536,393,930 qwen3.7-flash: 236,639,630 qwen3.8-flash: 215,228,820 qwen3.8-max: 105,236,795 qwen3.8-max-2026-09-02: 4,442,460 qwen3.7-plus: 3,315,325 qwen3-vl-plus: 1,722,455 qwen3.6-35b-a3b: 1,255,3302026-11-01 — 1,400,892,885 tokens qwen3.7-flash: 806,203,010 qwen3.8-flash: 274,655,980 51 more models: 187,518,950 qwen3.8-max: 122,817,305 qwen3.6-35b-a3b: 4,824,580 qwen3.8-max-2026-09-02: 4,261,545 qwen3.7-plus: 424,990 qwen3-vl-plus: 186,5252026-11-02 — 4,053,659,010 tokens qwen3.7-flash: 2,371,895,810 qwen3.8-flash: 1,055,885,800 51 more models: 473,557,050 qwen3-vl-plus: 70,522,995 qwen3.8-max: 47,860,250 qwen3.8-max-2026-09-02: 23,050,445 qwen3.6-35b-a3b: 6,749,375 qwen3.7-plus: 4,137,2852026-11-03 — 3,476,918,135 tokens qwen3.8-flash: 1,677,190,685 qwen3.7-flash: 905,966,275 51 more models: 489,327,290 qwen3.8-max-2026-09-02: 225,879,465 qwen3.8-max: 109,704,765 qwen3.7-plus: 66,190,320 qwen3-vl-plus: 2,642,210 qwen3.6-35b-a3b: 17,1252026-11-04 — 6,592,342,575 tokens qwen3.7-flash: 3,445,216,180 qwen3.8-flash: 1,346,700,400 51 more models: 715,702,985 qwen3-vl-plus: 672,905,455 qwen3.8-max-2026-09-02: 172,688,975 qwen3.8-max: 162,271,195 qwen3.6-35b-a3b: 51,623,915 qwen3.7-plus: 25,233,4702026-11-05 — 3,673,277,000 tokens qwen3.8-flash: 1,801,247,115 51 more models: 813,467,740 qwen3-vl-plus: 442,660,870 qwen3.8-max: 256,176,685 qwen3.8-max-2026-09-02: 147,788,285 qwen3.7-flash: 112,477,195 qwen3.6-35b-a3b: 79,679,100 qwen3.7-plus: 19,780,0102026-11-06 — 7,683,495,720 tokens qwen3.8-max: 4,979,335,900 qwen3.8-flash: 1,463,911,430 51 more models: 553,114,940 qwen3.7-flash: 322,479,415 qwen3-vl-plus: 299,390,455 qwen3.7-plus: 36,960,460 qwen3.6-35b-a3b: 19,070,795 qwen3.8-max-2026-09-02: 9,232,3252026-11-07 — 3,421,881,440 tokens qwen3.8-max: 1,352,973,780 qwen3.8-flash: 1,294,118,330 51 more models: 277,092,965 qwen3-vl-plus: 243,723,850 qwen3.7-flash: 173,818,550 qwen3.7-plus: 58,830,820 qwen3.8-max-2026-09-02: 11,913,625 qwen3.6-35b-a3b: 9,409,5202026-11-08 — 4,401,602,785 tokens qwen3.8-max: 2,294,079,685 qwen3.8-flash: 1,300,346,815 51 more models: 322,715,390 qwen3-vl-plus: 304,333,640 qwen3.7-plus: 60,369,080 qwen3.7-flash: 49,168,775 qwen3.8-max-2026-09-02: 45,511,320 qwen3.6-35b-a3b: 25,078,0802026-11-09 — 4,430,114,070 tokens qwen3.8-flash: 1,728,581,815 qwen3.8-max: 1,702,840,095 51 more models: 459,216,500 qwen3-vl-plus: 307,303,760 qwen3.8-max-2026-09-02: 126,322,325 qwen3.7-flash: 81,967,475 qwen3.7-plus: 13,863,260 qwen3.6-35b-a3b: 10,018,8402026-11-10 — 7,979,337,375 tokens qwen3.8-max: 4,886,358,165 qwen3.8-flash: 1,842,124,845 51 more models: 403,656,435 qwen3-vl-plus: 274,420,040 qwen3.6-35b-a3b: 207,847,285 qwen3.7-plus: 160,769,270 qwen3.8-max-2026-09-02: 126,681,350 qwen3.7-flash: 77,479,9852026-11-11 — 3,222,128,965 tokens qwen3.8-flash: 1,270,834,550 coding-qwen4-max-preview: 550,748,140 51 more models: 408,703,170 qwen3.7-plus: 333,068,255 qwen3.8-max: 232,831,120 qwen3.6-35b-a3b: 149,993,070 qwen3.7-flash: 139,649,185 qwen3.8-max-2026-09-02: 132,738,445 qwen3-vl-plus: 3,563,0302026-11-12 — 2,059,567,470 tokens qwen3.8-flash: 557,457,935 51 more models: 371,434,210 qwen3.6-35b-a3b: 348,297,675 qwen3.7-plus: 258,063,095 qwen3.7-flash: 173,105,350 coding-qwen4-max-preview: 156,380,135 qwen3.8-max: 94,700,920 qwen3-vl-plus: 84,747,945 qwen3.8-max-2026-09-02: 15,380,2052026-11-13 — 1,792,802,770 tokens 51 more models: 597,775,215 qwen3-vl-plus: 289,205,195 qwen3.8-flash: 235,331,095 qwen3.6-35b-a3b: 181,274,745 qwen3.7-plus: 167,635,620 qwen3.7-flash: 154,874,110 qwen3.8-max-2026-09-02: 143,484,030 qwen3.8-max: 22,160,730 coding-qwen4-max-preview: 1,062,0302026-11-14 — 1,662,915,885 tokens qwen3.8-flash: 814,903,795 51 more models: 394,667,560 qwen3.7-flash: 167,281,850 qwen3.8-max-2026-09-02: 104,094,795 qwen3.6-35b-a3b: 74,656,675 qwen3.8-max: 70,533,660 qwen3.7-plus: 20,867,665 coding-qwen4-max-preview: 13,755,645 qwen3-vl-plus: 2,154,2402026-11-15 — 1,674,529,005 tokens coding-qwen4-max-preview: 756,227,785 qwen3.8-flash: 371,744,100 qwen3.8-max: 244,419,200 51 more models: 144,730,135 qwen3.7-flash: 66,356,755 qwen3.8-max-2026-09-02: 43,249,460 qwen3.7-plus: 41,191,690 qwen3.6-35b-a3b: 4,424,370 qwen3-vl-plus: 2,185,5102026-11-16 — 1,675,543,415 tokens 51 more models: 708,017,360 qwen3.8-flash: 335,323,340 qwen3.6-35b-a3b: 240,866,955 qwen3.7-flash: 135,807,155 qwen3.8-max: 75,423,450 qwen3.8-max-2026-09-02: 58,959,675 coding-qwen4-max-preview: 57,359,330 qwen3-vl-plus: 36,208,240 qwen3.7-plus: 27,577,9102026-11-17 — 1,846,348,575 tokens 51 more models: 665,393,600 qwen3.8-flash: 473,408,850 qwen3.7-flash: 236,846,495 qwen3.7-plus: 187,217,920 qwen3.6-35b-a3b: 183,547,235 qwen3.8-max: 82,192,825 qwen3.8-max-2026-09-02: 13,699,170 qwen3-vl-plus: 3,117,880 coding-qwen4-max-preview: 924,6002026-11-18 — 1,584,826,365 tokens 51 more models: 511,473,785 qwen3.7-flash: 206,403,815 qwen3.8-flash: 194,257,505 qwen3.7-plus: 177,696,100 qwen3-vl-plus: 174,106,425 coding-qwen4-max-preview: 158,185,705 qwen3.6-35b-a3b: 81,268,045 qwen3.8-max: 79,730,300 qwen3.8-max-2026-09-02: 1,704,6852026-11-19 — 1,706,548,110 tokens 51 more models: 535,453,210 qwen3.8-flash: 281,537,820 qwen3-vl-plus: 262,988,520 qwen3.7-flash: 261,086,025 qwen3.7-plus: 228,171,695 qwen3.8-max: 67,258,925 qwen3.6-35b-a3b: 48,705,920 coding-qwen4-max-preview: 17,621,845 qwen3.8-max-2026-09-02: 3,724,1502026-11-20 — 1,254,711,880 tokens 51 more models: 435,169,360 qwen3.8-flash: 362,131,580 coding-qwen4-max-preview: 188,375,455 qwen3.7-flash: 120,002,530 qwen3.7-plus: 116,240,905 qwen3.8-max: 26,421,775 qwen3.6-35b-a3b: 3,364,240 qwen3-vl-plus: 2,793,495 qwen3.8-max-2026-09-02: 212,5402026-11-21 — 1,156,431,190 tokens 51 more models: 290,131,325 coding-qwen4-max-preview: 281,999,745 qwen3.8-flash: 254,522,320 qwen3-vl-plus: 161,482,185 qwen3.7-flash: 145,212,245 qwen3.7-plus: 13,819,330 qwen3.8-max-2026-09-02: 5,531,930 qwen3.8-max: 3,543,450 qwen3.6-35b-a3b: 188,660
  • qwen3.8-flash
  • qwen3.8-max
  • qwen3.7-flash
  • qwen3-vl-plus
  • qwen3.7-plus
  • coding-qwen4-max-preview
  • qwen3.6-35b-a3b
  • qwen3.8-max-2026-09-02
  • 51 more models

Which models that traffic went to

  1. Qwen3.8 Flash28.5%27.9B
  2. Qwen3.8 Max23.5%23B
  3. Qwen3.7 Flash20.7%20.2B
  4. Qwen3 VL Plus3.8%3.7B
  5. Qwen3.7 Plus2.4%2.3B
  6. Coding Qwen4 Max Preview2.2%2.2B
  7. Qwen3.6 35B A3B2.1%2B
  8. Qwen3.8 Max 2026 09-022.0%1.9B
  9. 51 more models14.8%14.5B

Share of 97.9B tokens. 76 models with traffic report no token counts and cannot be ranked here, including qwen-image-2.1-turbo and qwen-image-3.0-pro — 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 156 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 156 Qwen Models

Open in model list
Qwen 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
qwen3-coder-plusTakes text, returns text.1.05M66K$0.54$2.16/M$0.108/M—83 tok/s1.63 s
qwen3.6-plus-preview-freeTakes text, returns text.1M66KFreeFree/M————
qwen3.8-flash-freeTakes text, vision, video, returns text.1M131KFreeFree/M————
qwen3.8-max-freeTakes text, vision, video, returns text.1M131KFreeFree/M————
qwen3.5-flashTakes text, vision, video, returns text.1M66K$0.0282$0.282/M$0.0028/M$0.0352/M52 tok/s1.83 s
qwen3.7-flashTakes text, vision, video, returns text.1M131K$0.0282$0.1128/M$0.0056/M$0.0352/M32 tok/s20.21 s
qwen3.5-plusTakes text, vision, video, returns text.1M66K$0.1096$0.6576/M$0.011/M$0.137/M49 tok/s0.90 s
qwen3.8-flashTakes text, vision, video, returns text.1M131K$0.1126$0.38/M$0.0141/M$0.1759/M55 tok/s3.84 s
qwen3.8-omni-flashTakes text, vision, audio, video, returns text.1M131K$0.1126$0.38/M$0.0141/M$0.1759/M28 tok/s26.01 s
qwen3-coder-flashTakes text, returns text.1M66K$0.136$0.544/M——110 tok/s1.85 s
qwen3.6-flashTakes text, vision, video, returns text.1M66K$0.169$1.014/M$0.0169/M$0.2112/M63 tok/s11.30 s
qwen3.8-27bTakes text, vision, video, returns text.1M131K$0.2$2.5/M$0.05/M———
qwen3.6-plusTakes text, vision, video, returns text.1M66K$0.282$1.692/M$0.0282/M$0.3525/M54 tok/s2.27 s
qwen3.7-plusTakes text, vision, video, returns text.1M131K$0.282$1.128/M$0.0564/M$0.3525/M29 tok/s3.94 s
qwen3.8-max-previewTakes text, vision, video, returns text.1M131K$0.338$1.014/M$0.0676/M$0.4225/M48 tok/s2.40 s
coding-qwen4-max-previewTakes text, vision, video, returns text.1M393K$0.353$1.059/M$0.0441/M$0.4412/M37 tok/s4.22 s
qwen4-maxTakes text, vision, video, returns text.1M262K$1.471$4.412/M$0.0736/M$1.8388/M35 tok/s12.38 s
qwen3.7-maxTakes text, returns text.1M131K$1.69$5.07/M$0.169/M$2.1125/M50 tok/s2.80 s
qwen3.8-maxTakes text, vision, video, returns text.1M131K$1.69$5.07/M$0.169/M$2.1125/M27 tok/s2.32 s
qwen3.8-max-2026-09-02Takes text, vision, video, returns text.1M131K$1.69$5.07/M$0.169/M$2.1125/M11 tok/s3.86 s
qwen3.8-2.4t-a95bTakes text, returns text.1M131K$2$6/M$0.5/M—48 tok/s1.41 s
qwen3-vl-flashTakes text, vision, video, returns text.262K33K$0.0206$0.206/M$0.0041/M—5 tok/s0.34 s
qwen3-vl-flash-2026-01-22Takes text, vision, video, returns text.262K33K$0.0206$0.206/M——2 tok/s1.04 s
qwen3.5-35b-a3bTakes text, vision, video, returns text.262K66K$0.0564$0.4512/M——59 tok/s4.14 s
qwen3.5-27bTakes text, vision, video, returns text.262K66K$0.0846$0.6768/M——54 tok/s2.03 s
qwen3.5-122b-a10bTakes text, vision, video, returns text.262K66K$0.1126$0.9008/M——129 tok/s1.00 s
qwen3-coder-nextTakes text, returns text.262K66K$0.137$0.548/M——16 tok/s0.51 s
qwen3-vl-plusTakes text, vision, video, returns text.262K33K$0.137$1.37/M$0.0274/M—67 tok/s2.32 s
qwen3.5-397b-a17bTakes text, vision, video, returns text.262K66K$0.1644$0.9864/M——55 tok/s1.83 s
qwen3-coder-30b-a3b-instructTakes text, returns text.262K262K$0.2$0.8/M——115 tok/s0.95 s
qwen3.6-35b-a3bTakes text, vision, video, returns text.262K66K$0.254$1.524/M——99 tok/s1.14 s
qwen3-235b-a22b-instruct-2507Takes text, vision, returns text.262K16K$0.28$1.12/M——96 tok/s1.03 s
qwen3-235b-a22b-thinking-2507Takes text, vision, returns text.262K131K$0.28$2.8/M——87 tok/s0.51 s
qwen3-235b-a22b-2507Takes text, returns text.262K—$0.35$1.4/M$0.07/M———
qwen3.6-27bTakes text, vision, video, returns text.262K66K$0.422$2.532/M——81 tok/s1.84 s
qwen3-maxTakes text, returns text.262K66K$0.4508$1.8032/M$0.0902/M$0.5635/M36 tok/s2.41 s
qwen3-max-2026-01-23Takes text, returns text.262K66K$0.4508$1.8032/M$0.0902/M$0.5635/M——
qwen3.6-max-previewTakes text, returns text.262K66K$1.268$7.608/M$0.1268/M$1.585/M185 tok/s0.65 s
qwen3-coder-480b-a35b-instructTakes text, returns text.262K66K$0.82$3.28/M——1655 tok/s0.92 s
qwen3-next-80b-a3b-instructTakes text, vision, returns text.256K33K$0.138$0.552/M——150 tok/s0.10 s
qwen3-next-80b-a3b-thinkingTakes text, vision, returns text.256K33K$0.142$1.42/M——109 tok/s0.55 s
qwen3-vl-30b-a3b-instructTakes text, vision, video, returns text.131K33K$0.1028$0.4112/M——42 tok/s1.07 s
qwen3-vl-30b-a3b-thinkingTakes text, vision, video, returns text.131K33K$0.1028$1.028/M——42 tok/s1.49 s
qwen3-vl-235b-a22b-instructTakes text, vision, video, returns text.131K33K$0.274$1.096/M——57 tok/s1.13 s
qwen3-vl-235b-a22b-thinkingTakes text, vision, video, returns text.131K33K$0.274$2.74/M——58 tok/s2.22 s
qwen-3.8-27bTakes text, vision, video, returns text.131K—$1.1$1.65/M——562 tok/s0.40 s
bai-qwen3-vl-235b-a22b-instructTakes , returns text.131K—$0.274$1.096/M——5 tok/s0.39 s
kat-devTakes text, returns text.128K—$0.137$0.548/M————
Qwen/Qwen2.5-VL-72B-InstructTakes text, vision, video, returns text.128K—$0.5$0.5/M————
qwen3-coder-plus-2025-07-22Takes text, returns text.128K66K$0.54$2.16/M$0.108/M—83 tok/s1.63 s
decision-model-previewTakes text. Output modality not published.64K—FreeFree/M————
qwen3-reranker-0.6bTakes text, vision. Output modality not published.16K8K$0.11$0.11/M————
qwen-mt-turboTakes text, returns text.16K8K$0.192$0.5349/M——1 tok/s1.10 s
qwen-mt-plusTakes text, returns text.16K8K$0.492$1.476/M——8 tok/s0.30 s
wan3.0-video-freeTakes text, vision, audio, video, PDF, returns video.——FreeFree/M————
wan3.0-video-prime-freeTakes text, vision, audio, video, PDF, returns video.——FreeFree/M————
qwen-flashTakes , returns text.——$0.02$0.2/M——34 tok/s0.40 s
qwen-flash-2025-07-28Takes , returns text.——$0.02$0.2/M——2 tok/s0.39 s
qwen-turboTakes text, returns text.——$0.046$0.092/M$0.0092/M—23 tok/s0.84 s
qwen-turbo-2024-11-01Takes text, returns text.——$0.046$0.092/M——94 tok/s0.66 s
qwen-turbo-2025-04-28Takes , returns text.——$0.046$0.092/M————
qwen-turbo-latestTakes , returns text.——$0.046$0.092/M$0.0092/M———
qwen3-0.6bTakes , returns text.——$0.046$0.46/M————
qwen3-1.7bTakes , returns text.——$0.046$0.46/M————
qwen3-4bTakes , returns text.——$0.046$0.46/M————
bce-reranker-baseTakes text, vision. Output modality not published.——$0.068$0.068/M————
qwen3-embedding-0.6bTakes text. Output modality not published.——$0.068$0.068/M————
qwen3-embedding-4bTakes text. Output modality not published.——$0.068$0.068/M————
qwen3-embedding-8bTakes text. Output modality not published.——$0.068$0.068/M————
Qwen/Qwen2-7B-InstructTakes , returns text.——$0.08$0.08/M————
qwen3-8bTakes , returns text.——$0.08$0.8/M——62 tok/s0.39 s
text-embedding-v4Takes text. Output modality not published.——$0.08$0.08/M————
qwen-longTakes , returns text.——$0.1$0.4/M——45 tok/s2.96 s
qwen3-30b-a3b-instruct-2507Takes , returns text.——$0.1028$0.4112/M————
gte-rerank-v2Takes text, vision. Output modality not published.——$0.11$0.11/M————
qwen3-reranker-4bTakes text, vision. Output modality not published.——$0.11$0.11/M————
qwen3-reranker-8bTakes text, vision. Output modality not published.——$0.11$0.11/M————
qwen-plusTakes , returns text.——$0.1126$1.126/M$0.0225/M$0.1407/M44 tok/s0.76 s
qwen-plus-2025-04-28Takes , returns text.——$0.1126$1.126/M$0.0225/M$0.1407/M2 tok/s0.37 s
qwen-plus-2025-07-28Takes , returns text.——$0.1126$1.126/M$0.0225/M$0.1407/M——
qwen-plus-latestTakes , returns text.——$0.1126$1.126/M$0.0225/M$0.1407/M35 tok/s0.68 s
qwen3-30b-a3bTakes , returns text.——$0.12$1.2/M————
qwen3-30b-a3b-thinking-2507Takes , returns text.——$0.12$1.2/M————
gme-qwen2-vl-2b-instructTakes text, vision, video. Output modality not published.——$0.138$0.138/M————
Qwen/QwQ-32BTakes , returns text.——$0.14$0.56/M————
Qwen/Qwen2.5-Coder-32B-InstructTakes , returns text.——$0.16$0.16/M————
Qwen/QwQ-32B-PreviewTakes , returns text.——$0.16$0.16/M————
qwen3-14bTakes , returns text.——$0.16$1.6/M——59 tok/s0.31 s
qwen3-32bTakes , returns text.——$0.16$0.64/M————
Qwen/Qwen2-1.5B-InstructTakes , returns text.——$0.2$0.2/M————
Qwen/Qwen3-8BTakes , returns text.——$0.2$0.2/M——11 tok/s3.31 s
qwen2.5-coder-1.5b-instructTakes , returns text.——$0.2$0.4/M————
qwen2.5-coder-7b-instructTakes , returns text.——$0.2$0.4/M————
qwen2.5-math-1.5b-instructTakes , returns text.——$0.2$0.2/M————
qwen2.5-math-7b-instructTakes , returns text.——$0.2$0.4/M————
Qwen/Qwen2-57B-A14B-InstructTakes , returns text.——$0.24$0.24/M————
Qwen/Qwen2.5-VL-32B-InstructTakes text, vision, video, returns text.——$0.24$0.24/M————
qwen-3-235b-a22b-instruct-2507Takes , returns text.——$0.28$1.4/M————
qwen-3-235b-a22b-thinking-2507Takes , returns text.——$0.28$2.8/M——2 tok/s34.08 s
Qwen2-VL-7B-InstructTakes text, vision, video, returns text.——$0.28$0.7/M————
Qwen3-235B-A22B-Thinking-2507Takes , returns text.——$0.28$2.8/M——87 tok/s0.51 s
qwen-maxTakes , returns text.——$0.38$1.52/M——9 tok/s1.71 s
qwen-max-0125Takes , returns text.——$0.38$1.52/M————
qwen-3-32bTakes , returns text.——$0.4$1.6/M————
qwen-qwq-32bTakes , returns text.——$0.4$0.8/M————
Qwen/Qwen2.5-7B-InstructTakes , returns text.——$0.4$0.4/M————
Qwen/Qwen3-32BTakes , returns text.——$0.4$0.8/M————
qwen2.5-14b-instructTakes , returns text.——$0.4$1.2/M————
qwen2.5-3b-instructTakes , returns text.——$0.4$0.8/M————
qwen2.5-7b-instructTakes , returns text.——$0.4$0.8/M————
Qwen/Qwen3-14BTakes , returns text.——$0.5$0.5/M————
Qwen/Qwen2.5-32B-InstructTakes , returns text.——$0.6$0.6/M——24 tok/s1.62 s
qwen2.5-32b-instructTakes , returns text.——$0.6$1.2/M————
Qwen/Qwen2-72B-InstructTakes , returns text.——$0.8$0.8/M————
Qwen/Qwen2.5-72B-InstructTakes , returns text.——$0.8$0.8/M————
Qwen/Qwen2.5-72B-Instruct-128KTakes , returns text.——$0.8$0.8/M————
qwen2.5-72b-instructTakes , returns text.——$0.8$2.4/M————
qwen2.5-math-72b-instructTakes , returns text.——$0.8$2.4/M————
qwen3-max-previewTakes text, vision, returns text.——$0.846$3.384/M$0.1692/M—2 tok/s0.58 s
Qwen/Qwen3-30B-A3BTakes , returns text.——$1$1/M————
Qwen/QVQ-72B-PreviewTakes , returns text.——$1.2$1.2/M————
Qwen2-VL-72B-InstructTakes text, vision, video, returns text.——$2.18$6.54/M————
qwen2.5-vl-72b-instructTakes text, vision, returns text.——$2.4$7.2/M————
qwen-max-longcontextTakes , returns text.——$7$21/M——2 tok/s0.48 s
happyhorse-1.0-i2vTakes text, vision, returns video.——from $0.1395 / s————
happyhorse-1.0-r2vTakes text, vision, returns video.——from $0.1395 / s————
happyhorse-1.0-t2vTakes text, returns video.——from $0.1395 / s————
happyhorse-1.0-video-editTakes text, vision, video, returns video.——from $0.1395 / s————
happyhorse-1.1-i2vTakes text, vision, returns video.——from $0.1395 / s————
happyhorse-1.1-r2vTakes text, vision, returns video.——from $0.1395 / s————
happyhorse-1.1-t2vTakes text, returns video.——from $0.1395 / s————
qwen-audio-3.0-tts-flashTakes text, returns audio.——$0.0142 / 1K chars————
qwen-audio-3.0-tts-plusTakes text, returns audio.——$0.0197 / 1K chars————
qwen-imageTakes text, vision, returns vision.——$0.036 / img————
qwen-image-2.0Takes text, vision, returns vision.——$0.0282 / img————
qwen-image-2.0-proTakes text, vision, returns vision.——$0.0704 / img————
qwen-image-2.1-proTakes text, vision, returns vision.——$0.0352 / img————
qwen-image-2.1-turboTakes text, vision, returns vision.——$0.0141 / img————
qwen-image-3.0Takes text, vision, returns vision.——$0.0254 / img————
qwen-image-3.0-proTakes text, vision, returns vision.——from $0.0357 / img————
qwen-image-editTakes text, vision, returns vision.——$0.042 / img————
qwen-image-maxTakes text, vision, returns vision.——$0.0704 / img————
wan2.2-i2v-plusTakes text, vision, returns video.——from $0.0192 / s————
wan2.5-i2v-previewTakes text, vision, returns video.——from $0.0411 / s————
wan2.5-t2v-previewTakes text, returns video.——from $0.0411 / s————
wan2.6-i2vTakes text, vision, returns video.——from $0.0904 / s————
wan2.6-t2iTakes text, vision, returns vision.——$0.0282 / img————
wan2.6-t2vTakes text, returns video.——from $0.0904 / s————
wan2.7-i2vTakes text, vision, audio, returns video.——from $0.0846 / s————
wan2.7-imageTakes text, vision, returns vision.——$0.0282 / img————
wan2.7-image-proTakes text, vision, returns vision.——$0.0704 / img————
wan2.7-r2vTakes text, vision, audio, video, returns video.——from $0.0846 / s————
wan2.7-t2vTakes text, audio, returns video.——from $0.0846 / s————
wan2.7-videoeditTakes text, vision, video, returns video.——from $0.0846 / s————
wan3.0-videoTakes text, vision, audio, video, returns video.——from $0.0423 / s————
wan3.0-video-primeTakes text, vision, audio, video, returns video.——from $0.0634 / 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.

Qwen on AIHubMix

Which Qwen model should I start with?

qwen3-vl-flash at $0.0206/M input — the cheapest entry here that declares tool calling, and it carries a 262K context. Move up to qwen-max-longcontext when answer quality matters more than cost, or to qwen3.6-plus-preview-free for long-form reasoning.

Which of these models reason before answering?

25 of the 156 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 (Qwen/…), 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 qwen4-max bills cache hits at 5% of the input rate and qwen3.5-flash bills cache hits at 10% 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 Qwen 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 Qwen in one line

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