Z.AI Models

73 modelsGeneral models free to startUp to 1.05M contextOfficial site ↗

Usage

Last 30 days · 2026-10-24 to 2026-11-22

Tokens

395B

Requests

2M

Models in use

65 of 73

Tokens per day, stacked by model

015.9B31.8B10-2410-3111-0711-1411-212026-10-24 — 6,971,341,090 tokens coding-glm-5.3: 2,861,898,160 coding-glm-5.3-flash: 1,645,169,870 35 more models: 898,928,035 glm-5.3-flash: 860,851,040 coding-glm-5.3-free: 268,817,345 coding-glm-5.1: 174,318,675 glm-5.3-flashx: 119,140,640 glm-5.3: 75,381,390 glm-5.2: 66,835,9352026-10-25 — 8,196,085,300 tokens coding-glm-5.3-flash: 2,376,536,615 glm-5.3-flash: 2,163,033,555 coding-glm-5.3: 2,063,271,185 35 more models: 929,771,845 coding-glm-5.3-free: 332,583,430 glm-5.3-flashx: 173,547,485 glm-5.2: 102,607,545 glm-5.3: 54,664,230 coding-glm-5.1: 69,4102026-10-26 — 8,420,726,575 tokens coding-glm-5.3: 2,190,950,065 glm-5.3-flash: 1,610,709,100 coding-glm-5.3-flash: 1,564,434,550 glm-5.3: 1,326,967,785 35 more models: 1,223,513,460 coding-glm-5.3-free: 261,667,850 glm-5.3-flashx: 156,682,640 glm-5.2: 83,010,445 coding-glm-5.1: 2,790,6802026-10-27 — 9,636,216,290 tokens coding-glm-5.3: 2,503,293,920 glm-5.3-flash: 1,950,761,235 coding-glm-5.3-flash: 1,931,086,045 glm-5.3: 1,575,785,410 35 more models: 828,615,130 coding-glm-5.3-free: 379,846,115 glm-5.3-flashx: 273,464,420 glm-5.2: 192,295,140 coding-glm-5.1: 1,068,8752026-10-28 — 11,813,599,990 tokens coding-glm-5.3-flash: 3,183,495,935 coding-glm-5.3: 2,584,541,555 glm-5.3: 2,239,216,560 glm-5.3-flash: 1,581,061,685 35 more models: 900,192,095 glm-5.3-flashx: 859,835,730 coding-glm-5.3-free: 355,881,400 glm-5.2: 75,582,665 coding-glm-5.1: 33,792,3652026-10-29 — 14,814,073,605 tokens glm-5.3-flash: 3,862,996,225 glm-5.3-flashx: 3,519,629,585 coding-glm-5.3: 2,660,036,085 coding-glm-5.3-flash: 2,519,216,035 glm-5.3: 1,058,851,720 35 more models: 644,963,140 coding-glm-5.3-free: 294,450,815 coding-glm-5.1: 156,863,090 glm-5.2: 97,066,9102026-10-30 — 31,801,743,370 tokens glm-5.3: 19,252,284,815 coding-glm-5.3-flash: 4,767,751,450 coding-glm-5.3: 3,814,282,060 glm-5.3-flash: 1,974,925,405 35 more models: 728,035,110 glm-5.3-flashx: 427,834,595 coding-glm-5.3-free: 346,159,850 glm-5.2: 343,887,000 coding-glm-5.1: 146,583,0852026-10-31 — 9,428,681,470 tokens coding-glm-5.3: 3,680,796,100 coding-glm-5.3-flash: 2,082,635,275 glm-5.3: 1,375,971,915 glm-5.3-flash: 809,454,335 35 more models: 607,887,680 glm-5.2: 443,199,935 coding-glm-5.3-free: 261,987,860 glm-5.3-flashx: 150,736,450 coding-glm-5.1: 16,011,9202026-11-01 — 9,956,069,750 tokens glm-5.3: 4,985,167,695 coding-glm-5.3: 2,097,308,505 glm-5.3-flash: 1,026,735,670 35 more models: 622,319,270 coding-glm-5.3-flash: 364,847,770 glm-5.2: 361,730,125 coding-glm-5.3-free: 294,059,850 coding-glm-5.1: 146,451,495 glm-5.3-flashx: 57,449,3702026-11-02 — 13,944,480,095 tokens glm-5.3-flash: 8,187,285,935 coding-glm-5.3: 2,382,366,420 35 more models: 912,661,700 glm-5.3: 735,139,420 coding-glm-5.3-flash: 733,499,285 coding-glm-5.3-free: 330,723,160 glm-5.3-flashx: 262,157,390 glm-5.2: 261,320,680 coding-glm-5.1: 139,326,1052026-11-03 — 8,074,305,855 tokens coding-glm-5.3: 2,275,405,135 coding-glm-5.3-flash: 1,948,390,035 glm-5.3-flash: 1,254,463,720 glm-5.3: 879,944,350 35 more models: 802,702,865 coding-glm-5.3-free: 337,969,210 glm-5.3-flashx: 300,695,745 glm-5.2: 243,805,000 coding-glm-5.1: 30,929,7952026-11-04 — 8,828,349,590 tokens coding-glm-5.3: 3,462,764,320 glm-5.3-flash: 1,962,817,440 coding-glm-5.3-flash: 1,200,435,675 35 more models: 780,023,920 glm-5.3: 626,426,085 coding-glm-5.3-free: 333,797,225 glm-5.3-flashx: 245,542,595 coding-glm-5.1: 187,513,020 glm-5.2: 29,029,3102026-11-05 — 13,859,432,785 tokens glm-5.3-flash: 4,315,911,570 glm-5.3: 2,844,056,700 coding-glm-5.3: 2,533,200,225 coding-glm-5.3-flash: 2,286,762,625 35 more models: 713,546,830 coding-glm-5.1: 485,356,890 coding-glm-5.3-free: 343,797,715 glm-5.3-flashx: 243,781,380 glm-5.2: 93,018,8502026-11-06 — 19,379,260,030 tokens glm-5.3-flash: 6,244,259,360 glm-5.3: 4,438,327,420 coding-glm-5.3: 2,926,603,050 coding-glm-5.3-flash: 2,450,174,880 glm-5.3-flashx: 2,012,996,645 35 more models: 579,178,975 glm-5.2: 419,630,095 coding-glm-5.3-free: 282,684,425 coding-glm-5.1: 25,405,1802026-11-07 — 18,223,664,485 tokens glm-5.3-flash: 6,834,483,485 glm-5.3: 3,139,417,240 coding-glm-5.3: 2,810,880,885 glm-5.3-flashx: 2,033,711,445 coding-glm-5.3-flash: 1,817,712,925 35 more models: 864,730,615 coding-glm-5.3-free: 362,263,560 coding-glm-5.1: 283,496,775 glm-5.2: 76,967,5552026-11-08 — 14,338,502,305 tokens coding-glm-5.3: 4,463,654,130 glm-5.3: 3,614,813,730 glm-5.3-flash: 3,060,891,560 glm-5.3-flashx: 1,089,992,025 coding-glm-5.3-flash: 768,042,525 35 more models: 703,601,190 coding-glm-5.3-free: 336,257,860 coding-glm-5.1: 222,414,785 glm-5.2: 78,834,5002026-11-09 — 12,900,478,430 tokens coding-glm-5.3: 5,096,088,705 glm-5.3-flash: 2,816,370,885 coding-glm-5.3-flash: 1,624,304,020 35 more models: 1,142,990,950 glm-5.3: 1,108,097,125 glm-5.3-flashx: 522,348,700 coding-glm-5.3-free: 371,582,465 glm-5.2: 128,091,320 coding-glm-5.1: 90,604,2602026-11-10 — 20,069,527,990 tokens glm-5.3-flash: 11,706,314,370 coding-glm-5.3: 4,010,254,130 coding-glm-5.3-flash: 1,390,203,260 glm-5.3: 1,234,404,990 glm-5.3-flashx: 522,822,925 35 more models: 501,712,945 coding-glm-5.3-free: 332,667,425 coding-glm-5.1: 289,807,775 glm-5.2: 81,340,1702026-11-11 — 12,206,158,900 tokens coding-glm-5.3: 4,679,305,200 glm-5.3-flash: 3,124,133,805 glm-5.3: 1,568,758,715 coding-glm-5.3-flash: 1,032,380,585 35 more models: 661,528,495 coding-glm-5.3-free: 489,776,200 coding-glm-5.1: 353,963,595 glm-5.3-flashx: 237,160,610 glm-5.2: 59,151,6952026-11-12 — 14,040,281,250 tokens glm-5.3-flash: 4,447,679,895 coding-glm-5.3: 3,302,286,020 coding-glm-5.3-flash: 2,734,769,805 glm-5.3: 1,697,796,135 glm-5.3-flashx: 653,563,845 coding-glm-5.3-free: 422,114,775 35 more models: 417,922,895 coding-glm-5.1: 283,337,770 glm-5.2: 80,810,1102026-11-13 — 16,532,277,020 tokens glm-5.3-flash: 9,028,722,020 coding-glm-5.3: 2,769,329,285 coding-glm-5.3-flash: 1,426,774,355 glm-5.3: 1,274,031,715 glm-5.3-flashx: 603,180,255 coding-glm-5.3-free: 578,314,075 35 more models: 407,981,935 coding-glm-5.1: 320,830,825 glm-5.2: 123,112,5552026-11-14 — 8,301,225,620 tokens coding-glm-5.3: 3,356,366,715 glm-5.3-flash: 1,731,770,850 coding-glm-5.3-flash: 1,483,434,230 35 more models: 459,021,805 glm-5.3-flashx: 359,868,065 coding-glm-5.3-free: 357,024,765 glm-5.2: 335,215,100 glm-5.3: 183,398,050 coding-glm-5.1: 35,126,0402026-11-15 — 21,767,665,320 tokens coding-glm-5.3-flash: 7,894,227,985 coding-glm-5.3: 7,582,973,310 glm-5.3-flash: 2,818,105,560 glm-5.3: 1,442,386,125 35 more models: 676,875,070 glm-5.2: 489,741,100 coding-glm-5.3-free: 313,940,230 coding-glm-5.1: 307,439,840 glm-5.3-flashx: 241,976,1002026-11-16 — 13,903,599,945 tokens glm-5.3-flash: 7,160,659,870 coding-glm-5.3: 2,575,233,540 coding-glm-5.3-flash: 838,139,215 glm-5.2: 769,875,160 glm-5.3-flashx: 735,223,085 35 more models: 735,135,750 glm-5.3: 449,649,350 coding-glm-5.3-free: 386,640,355 coding-glm-5.1: 253,043,6202026-11-17 — 10,000,008,760 tokens glm-5.3-flash: 2,858,424,685 coding-glm-5.3: 2,696,241,825 coding-glm-5.3-flash: 1,232,181,870 35 more models: 809,128,150 glm-5.2: 549,374,095 coding-glm-5.1: 525,006,670 glm-5.3-flashx: 479,911,210 coding-glm-5.3-free: 462,106,760 glm-5.3: 387,633,4952026-11-18 — 13,448,700,745 tokens glm-5.3-flash: 5,496,858,040 coding-glm-5.3: 2,194,532,890 coding-glm-5.3-flash: 1,805,177,615 glm-5.3: 1,270,620,025 35 more models: 870,676,650 glm-5.3-flashx: 641,470,450 coding-glm-5.1: 552,086,590 coding-glm-5.3-free: 450,880,260 glm-5.2: 166,398,2252026-11-19 — 9,142,759,305 tokens glm-5.3-flash: 2,831,542,085 coding-glm-5.3: 2,097,244,830 coding-glm-5.3-flash: 1,724,067,930 35 more models: 686,119,400 glm-5.3: 646,119,880 glm-5.3-flashx: 477,230,685 coding-glm-5.3-free: 330,021,400 coding-glm-5.1: 305,034,835 glm-5.2: 45,378,2602026-11-20 — 12,135,475,125 tokens glm-5.3-flash: 4,090,651,415 coding-glm-5.3: 2,726,822,425 coding-glm-5.3-flash: 1,983,637,565 glm-5.3: 1,361,112,320 glm-5.3-flashx: 819,320,230 35 more models: 607,910,435 coding-glm-5.3-free: 364,450,490 coding-glm-5.1: 130,299,715 glm-5.2: 51,270,5302026-11-21 — 13,537,778,505 tokens glm-5.3-flash: 6,926,253,305 coding-glm-5.3: 1,803,302,625 glm-5.3: 1,620,906,350 coding-glm-5.3-flash: 950,230,575 35 more models: 802,532,945 glm-5.3-flashx: 536,483,405 coding-glm-5.1: 363,930,915 coding-glm-5.3-free: 358,510,425 glm-5.2: 175,627,9602026-11-22 — 8,887,915,935 tokens coding-glm-5.3: 2,633,013,315 glm-5.3-flashx: 1,838,279,470 glm-5.3-flash: 1,467,757,545 glm-5.3: 1,260,836,170 35 more models: 651,998,180 coding-glm-5.3-flash: 513,338,560 coding-glm-5.3-free: 364,324,000 coding-glm-5.1: 85,128,450 glm-5.2: 73,240,245
  • glm-5.3-flash
  • coding-glm-5.3
  • glm-5.3
  • coding-glm-5.3-flash
  • glm-5.3-flashx
  • coding-glm-5.3-free
  • glm-5.2
  • coding-glm-5.1
  • 35 more models

Which models that traffic went to

  1. GLM 5.3 Flash28.9%114B
  2. Coding GLM 5.323.5%92.8B
  3. GLM 5.316.2%63.7B
  4. Coding GLM 5.3 Flash14.8%58.3B
  5. GLM 5.3 Flashx5.2%20.6B
  6. Coding GLM 5.3 (free)2.7%10.7B
  7. GLM 5.21.5%6.1B
  8. Coding GLM 5.11.5%5.9B
  9. 35 more models5.6%22.2B

Share of 395B tokens. 22 models with traffic report no token counts and cannot be ranked here, including coding-glm-5-turbo-free and alicloud-glm-4.7 — 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 73 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 73 Z.AI Models

Open in model list
Z.AI 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-glm-5.3-freeTakes text, returns text.1.05M131KFreeFree/M—50 tok/s3.80 s
ox-alphaTakes text, vision, video, returns text.1.05M131KFreeFree/M———
coding-glm-5.3Takes text, returns text.1.05M131K$0.06$0.22/M$0.015/M43 tok/s5.04 s
glm-5.3-flashTakes text, vision, video, returns text.1.05M131K$0.1127$0.3944/M$0.0324/M68 tok/s0.31 s
glm-5.3Takes text, returns text.1.05M131K$1.1268$3.9438/M$0.2817/M42 tok/s0.65 s
glm-5.3-primeTakes text, returns text.1.05M131K$2.35$8.23/M$0.59/M22 tok/s5.06 s
coding-glm-5.2-freeTakes text, returns text.1M131KFreeFree/M—50 tok/s3.70 s
coding-glm-5.3-flash-freeTakes text, vision, video, returns text.1M131KFreeFree/M—41 tok/s3.95 s
coding-glm-5.3-flashTakes text, vision, video, returns text.1M131K$0.0282$0.0986/M$0.007/M32 tok/s8.93 s
coding-glm-5.2Takes text, returns text.1M131K$0.06$0.22/M—52 tok/s3.66 s
glm-5.3-flashxTakes text, vision, video, returns text.1M—$0.282$0.987/M$0.0804/M75 tok/s3.67 s
glm-5.2Takes text, returns text.1M131K$1.1268$3.9438/M$0.2817/M46 tok/s1.04 s
cloudflare-glm-5.2Takes text, returns text.1M131K$1.4$4.4002/M$0.2604/M——
glm-5.2-fast-previewTakes text, returns text.1M131K$2.254$7.889/M$0.5635/M38 tok/s2.00 s
coding-glm-5-turbo-freeTakes text, returns text.205K131KFreeFree/M———
cc-glm-5-turboTakes text, returns text.205K131K$0.06$0.22/M—40 tok/s1.19 s
coding-glm-5-turboTakes text, returns text.205K131K$0.06$0.22/M———
glm-5-turboTakes text, returns text.205K131K$1.2$3.9996/M$0.24/M25 tok/s1.47 s
zai-glm-5-turboTakes text, returns text.205K131K$1.2$3.9996/M$0.24/M25 tok/s1.47 s
coding-glm-4.6-freeTakes text, returns text.200K131KFreeFree/M—45 tok/s4.08 s
coding-glm-4.7-freeTakes text, returns text.200K131KFreeFree/M—44 tok/s3.21 s
coding-glm-5-freeTakes text, returns text.200K131KFreeFree/M—35 tok/s2.80 s
coding-glm-5.1-freeTakes text, returns text.200K131KFreeFree/M—184 tok/s2.77 s
glm-4.7-flash-freeTakes text, returns text.200K131KFreeFree/M—30 tok/s21.76 s
cc-glm-5Takes text, returns text.200K131K$0.06$0.22/M—21 tok/s2.60 s
cc-glm-5.1Takes text, returns text.200K131K$0.06$0.22/M———
coding-glm-4.6Takes text, returns text.200K131K$0.06$0.22/M$0.011/M48 tok/s1.29 s
coding-glm-4.7Takes text, returns text.200K131K$0.06$0.22/M$0.011/M47 tok/s1.19 s
coding-glm-5Takes text, returns text.200K131K$0.06$0.22/M—21 tok/s8.01 s
coding-glm-5.1Takes text, returns text.200K131K$0.06$0.22/M—54 tok/s4.89 s
glm-4.6Takes text, returns text.200K131K$0.274$1.0959/M$0.0548/M32 tok/s1.79 s
glm-4.7Takes text, returns text.200K131K$0.274$1.0959/M$0.0548/M54 tok/s2.70 s
glm-5v-turboTakes text, vision, video, returns text.200K131K$0.7042$3.0985/M$0.169/M36 tok/s0.75 s
glm-5.1Takes text, returns text.200K131K$0.845$3.38/M$0.1831/M26 tok/s0.86 s
coding-glm-4.5-airTakes text, returns text.131K—$0.014$0.084/M—46 tok/s5.43 s
glm-4.6vTakes text, vision, video, returns text.131K33K$0.137$0.411/M$0.0274/M40 tok/s0.91 s
glm-4.5-airTakes text, returns text.131K98K$0.14$0.84/M—91 tok/s0.67 s
glm-4.5Takes text, returns text.131K98K$0.4$1.6/M—93 tok/s0.46 s
glm-4.5vTakes text, vision, video, returns text.66K16K$0.274$0.822/M—81 tok/s8.45 s
glm-ocrTakes vision, returns text.32K—$0.0282$0.0282/M———
embedding-2Takes text. Output modality not published.8K—$0.0686$0.0686/M———
embedding-3Takes text. Output modality not published.8K—$0.0686$0.0686/M———
Pro/THUDM/GLM-4.1V-9B-ThinkingTakes , returns text.——$0.04$0.16/M———
THUDM/GLM-4-9B-0414Takes , returns text.——$0.05$0.05/M———
THUDM/GLM-Z1-9B-0414Takes , returns text.——$0.05$0.05/M———
cc-glm-4.6Takes , returns text.——$0.06$0.22/M—30 tok/s1.02 s
cc-glm-4.7Takes , returns text.——$0.06$0.22/M—8 tok/s1.47 s
coding-glm-5.5Takes text, returns text.——$0.06$0.22/M$0.015/M——
THUDM/GLM-4-32B-0414Takes , returns text.——$0.08$0.08/M———
THUDM/GLM-Z1-32B-0414Takes , returns text.——$0.08$0.08/M———
glm-4-flashTakes , returns text.——$0.1$0.1/M———
THUDM/GLM-4.1V-9B-ThinkingTakes , returns text.——$0.1$0.1/M———
doubao-1-5-pro-32k-250115Takes , returns text.——$0.108$0.27/M———
chatglm_liteTakes , returns text.——$0.2858$0.2858/M———
alicloud-glm-4.7Takes , returns text.——$0.411$1.9178/M$0.411/M44 tok/s1.01 s
alicloud-glm-5Takes , returns text.——$0.5634$2.5353/M$0.1127/M42 tok/s4.25 s
doubao-1-5-pro-256k-250115Takes , returns text.——$0.684$1.2312/M———
glm-3-turboTakes , returns text.——$0.71$0.71/M———
chatglm_stdTakes , returns text.——$0.7144$0.7144/M———
chatglm_turboTakes , returns text.——$0.7144$0.7144/M———
glm-4.5-airxTakes text, returns text.——$1.1$4.51/M$0.22/M41 tok/s0.67 s
chatglm_proTakes , returns text.——$1.4286$1.4286/M———
glm-4v-plusTakes , returns text.——$2$2/M———
glm-zero-previewTakes , returns text.——$2$2/M—39 tok/s0.73 s
glm-4.5-xTakes text, returns text.——$2.2$8.91/M$0.44/M19 tok/s1.58 s
cbs-glm-4.7Takes , returns text.——$2.25$2.75/M———
glm-4-plusTakes , returns text.——$8$8/M—29 tok/s0.60 s
cogview-3-plusTakes , returns vision.——$10$10/M———
glm-4Takes , returns text.——$14.2$14.2/M———
glm-4vTakes , returns text.——$14.2$14.2/M———
code-davinci-edit-001Takes , returns text.——$20$20/M———
cogview-3Takes , returns vision.——$35.5$35.5/M———
glm-imageTakes text, returns vision.——$0.015 / img———

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.

Z.AI on AIHubMix

Which Z.AI model should I start with?

coding-glm-4.6-free is free on input — the cheapest entry here that declares tool calling, and it carries a 200K context. Move up to cogview-3 when answer quality matters more than cost, or to coding-glm-5.3-free for long-form reasoning.

Which of these models reason before answering?

29 of the 73 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 (THUDM/…), 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 coding-glm-4.6 bills cache hits at 18.33% of the input rate and coding-glm-4.7 bills cache hits at 18.33% 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 Z.AI 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 Z.AI in one line

One key, one endpoint, 985 models across 49 model authors.