Grok Models

28 modelsGeneral models from $0.2/M inputUp to 2M context

Usage

Last 30 days · 2026-10-22 to 2026-11-20

Tokens

33.5B

Requests

582K

Models in use

25 of 28

Tokens per day, stacked by model

01.8B3.6B10-2210-2911-0511-1211-192026-10-22 — 787,031,745 tokens grok-4-20-non-reasoning: 317,305,350 grok-4-1-fast-non-reasoning: 169,085,985 grok-4.6: 88,835,640 grok-4.7: 79,027,515 grok-4.3: 75,281,330 grok-4-1-fast-reasoning: 36,059,460 grok-4.5: 20,174,860 grok-4-20-reasoning: 1,261,6052026-10-23 — 843,471,060 tokens grok-4-20-non-reasoning: 282,401,835 grok-4-1-fast-non-reasoning: 201,336,915 grok-4.7: 140,409,825 grok-4.6: 91,515,900 grok-4.3: 80,433,200 grok-4.5: 28,306,040 grok-4-1-fast-reasoning: 17,012,405 grok-4-20-reasoning: 2,054,9402026-10-24 — 802,398,075 tokens grok-4.3: 412,052,065 grok-4-1-fast-non-reasoning: 201,883,620 grok-4-1-fast-reasoning: 75,575,160 grok-4.5: 54,614,470 grok-4.7: 53,009,780 grok-4.6: 5,209,670 1 more model: 53,3102026-10-25 — 3,562,687,420 tokens grok-4.7: 2,822,715,130 grok-4.3: 465,016,140 grok-4-1-fast-non-reasoning: 182,019,185 grok-4-1-fast-reasoning: 55,461,205 grok-4.6: 24,923,745 grok-4.5: 12,552,0152026-10-26 — 900,262,565 tokens grok-4-20-non-reasoning: 241,224,030 grok-4-1-fast-non-reasoning: 190,618,420 grok-4.3: 185,542,235 grok-4.6: 106,277,560 grok-4.7: 72,538,150 grok-4.5: 59,470,805 grok-4-1-fast-reasoning: 44,542,080 grok-4-20-reasoning: 49,2852026-10-27 — 1,270,695,890 tokens grok-4-20-non-reasoning: 488,272,855 grok-4.5: 285,577,320 grok-4-1-fast-non-reasoning: 213,091,250 grok-4.7: 161,028,695 grok-4.6: 70,790,625 grok-4-1-fast-reasoning: 34,443,620 grok-4.3: 9,346,090 grok-4-20-reasoning: 8,145,4352026-10-28 — 1,362,580,850 tokens grok-4-20-non-reasoning: 408,454,450 grok-4.7: 316,415,565 grok-4.5: 217,135,535 grok-4-1-fast-non-reasoning: 200,995,895 grok-4.6: 173,975,930 grok-4-20-reasoning: 22,631,300 grok-4-1-fast-reasoning: 11,811,870 grok-4.3: 11,160,3052026-10-29 — 885,483,595 tokens grok-4-20-non-reasoning: 305,293,210 grok-4.6: 202,876,490 grok-4-1-fast-non-reasoning: 195,770,965 grok-4.7: 117,010,120 grok-4.5: 43,688,770 grok-4-1-fast-reasoning: 11,850,720 grok-4.3: 7,142,820 grok-4-20-reasoning: 1,850,5002026-10-30 — 1,709,774,530 tokens grok-4.7: 721,515,410 grok-4-20-non-reasoning: 388,036,150 grok-4.6: 295,818,800 grok-4-1-fast-non-reasoning: 232,128,025 grok-4-1-fast-reasoning: 33,579,010 grok-4.3: 25,379,645 grok-4.5: 12,930,905 grok-4-20-reasoning: 386,5852026-10-31 — 626,511,600 tokens grok-4-20-non-reasoning: 332,134,440 grok-4-1-fast-non-reasoning: 189,840,825 grok-4.6: 48,493,035 grok-4.7: 17,789,915 grok-4.5: 13,940,205 grok-4-1-fast-reasoning: 10,424,490 grok-4.3: 9,374,350 grok-4-20-reasoning: 4,514,3402026-11-01 — 623,827,005 tokens grok-4-20-non-reasoning: 317,512,140 grok-4-1-fast-non-reasoning: 193,011,470 grok-4.7: 32,945,585 grok-4.6: 22,972,555 grok-4-1-fast-reasoning: 21,132,095 grok-4.3: 18,677,690 grok-4.5: 13,315,100 grok-4-20-reasoning: 4,260,3702026-11-02 — 933,889,910 tokens grok-4-20-non-reasoning: 332,067,760 grok-4.7: 300,657,355 grok-4-1-fast-non-reasoning: 212,058,265 grok-4.6: 42,742,140 grok-4-1-fast-reasoning: 23,669,835 grok-4.5: 16,705,755 grok-4.3: 3,371,975 grok-4-20-reasoning: 2,616,8252026-11-03 — 1,037,697,625 tokens grok-4-20-non-reasoning: 330,321,580 grok-4.7: 320,985,960 grok-4-1-fast-non-reasoning: 220,170,955 grok-4.6: 113,927,805 grok-4-1-fast-reasoning: 31,376,585 grok-4.5: 14,339,975 grok-4.3: 5,563,070 grok-4-20-reasoning: 1,011,6952026-11-04 — 1,462,394,850 tokens grok-4.7: 666,483,250 grok-4-20-non-reasoning: 301,751,150 grok-4-1-fast-non-reasoning: 278,738,125 grok-4.6: 148,277,535 grok-4-1-fast-reasoning: 34,187,590 grok-4-20-reasoning: 16,985,405 grok-4.5: 12,776,925 grok-4.3: 3,194,8702026-11-05 — 1,012,491,325 tokens grok-4.7: 332,828,000 grok-4-20-non-reasoning: 319,960,380 grok-4-1-fast-non-reasoning: 234,968,820 grok-4.6: 71,818,295 grok-4-1-fast-reasoning: 31,784,065 grok-4.5: 18,027,235 grok-4.3: 2,376,760 grok-4-20-reasoning: 727,7702026-11-06 — 651,472,820 tokens grok-4-20-non-reasoning: 248,577,025 grok-4-1-fast-non-reasoning: 155,495,715 grok-4.7: 123,311,590 grok-4.6: 53,015,805 grok-4.5: 44,363,815 grok-4-1-fast-reasoning: 24,912,245 grok-4.3: 1,200,545 grok-4-20-reasoning: 596,0802026-11-07 — 521,030,460 tokens grok-4-20-non-reasoning: 275,600,930 grok-4-1-fast-non-reasoning: 126,020,780 grok-4.5: 44,916,690 grok-4.7: 42,039,905 grok-4.6: 14,404,680 grok-4-1-fast-reasoning: 9,606,435 grok-4-20-reasoning: 4,327,915 grok-4.3: 4,061,595 1 more model: 51,5302026-11-08 — 662,132,470 tokens grok-4-20-non-reasoning: 249,577,865 grok-4.7: 122,204,585 grok-4-1-fast-non-reasoning: 114,065,780 grok-4.5: 78,283,040 grok-4-1-fast-reasoning: 46,804,770 grok-4.6: 40,684,265 grok-4.3: 8,012,315 grok-4-20-reasoning: 2,424,590 1 more model: 75,2602026-11-09 — 758,796,110 tokens grok-4-20-non-reasoning: 254,674,460 grok-4.7: 178,751,020 grok-4-1-fast-non-reasoning: 134,064,760 grok-4.5: 114,878,145 grok-4.6: 39,569,935 grok-4-1-fast-reasoning: 20,877,285 grok-4-20-reasoning: 9,999,475 grok-4.3: 4,466,865 1 more model: 1,514,1652026-11-10 — 721,587,770 tokens grok-4-20-non-reasoning: 225,758,720 grok-4.7: 201,531,460 grok-4-1-fast-non-reasoning: 148,824,230 grok-4.6: 51,044,165 grok-4.5: 46,346,760 grok-4-1-fast-reasoning: 23,390,775 grok-4.3: 20,406,790 grok-4-20-reasoning: 4,284,8702026-11-11 — 1,263,743,320 tokens grok-4.7: 534,776,635 grok-4-20-non-reasoning: 259,999,210 grok-4.6: 254,021,580 grok-4-1-fast-non-reasoning: 158,201,490 grok-4-1-fast-reasoning: 26,173,405 grok-4.5: 20,845,705 grok-4.3: 8,775,390 grok-4-20-reasoning: 949,9052026-11-12 — 1,480,706,495 tokens grok-4.7: 505,189,070 grok-4.6: 418,591,490 grok-4-20-non-reasoning: 283,242,890 grok-4-1-fast-non-reasoning: 150,017,055 grok-4-1-fast-reasoning: 78,480,415 grok-4-20-reasoning: 17,166,605 grok-4.5: 14,887,670 grok-4.3: 13,131,3002026-11-13 — 835,742,215 tokens grok-4.7: 341,739,935 grok-4-20-non-reasoning: 229,608,580 grok-4-1-fast-non-reasoning: 150,017,260 grok-4-1-fast-reasoning: 46,219,475 grok-4-20-reasoning: 32,987,685 grok-4.6: 18,332,460 grok-4.5: 11,734,325 grok-4.3: 5,102,4952026-11-14 — 525,254,110 tokens grok-4-20-non-reasoning: 242,217,220 grok-4-1-fast-non-reasoning: 125,489,280 grok-4-1-fast-reasoning: 50,198,755 grok-4.6: 40,074,910 grok-4.3: 32,934,180 grok-4.7: 26,492,765 grok-4.5: 5,797,195 grok-4-20-reasoning: 2,049,8052026-11-15 — 729,210,985 tokens grok-4-20-non-reasoning: 308,018,290 grok-4-1-fast-non-reasoning: 153,625,705 grok-4.7: 89,564,640 grok-4.3: 63,737,190 grok-4-1-fast-reasoning: 51,544,820 grok-4.6: 35,396,160 grok-4.5: 13,759,740 grok-4-20-reasoning: 13,564,4402026-11-16 — 1,489,436,935 tokens grok-4.6: 455,763,670 grok-4-20-non-reasoning: 399,112,345 grok-4.7: 337,819,705 grok-4-1-fast-non-reasoning: 199,898,340 grok-4-1-fast-reasoning: 44,002,240 grok-4-20-reasoning: 26,707,990 grok-4.5: 23,665,825 grok-4.3: 2,466,8202026-11-17 — 1,661,134,075 tokens grok-4.7: 645,741,405 grok-4-20-non-reasoning: 385,980,110 grok-4.6: 385,657,290 grok-4-1-fast-non-reasoning: 183,475,195 grok-4-1-fast-reasoning: 26,218,175 grok-4-20-reasoning: 17,180,210 grok-4.5: 15,603,010 grok-4.3: 1,278,6802026-11-18 — 1,770,329,310 tokens grok-4.7: 717,671,095 grok-4-20-non-reasoning: 432,557,310 grok-4.6: 360,686,645 grok-4-1-fast-non-reasoning: 183,748,495 grok-4-1-fast-reasoning: 23,119,875 grok-4-20-reasoning: 20,808,295 grok-4.5: 19,584,235 grok-4.3: 12,153,3602026-11-19 — 1,249,574,985 tokens grok-4-20-non-reasoning: 422,049,775 grok-4.7: 326,389,675 grok-4.6: 242,443,100 grok-4-1-fast-non-reasoning: 154,332,720 grok-4-1-fast-reasoning: 45,297,190 grok-4.5: 31,342,090 grok-4-20-reasoning: 23,156,340 grok-4.3: 4,564,0952026-11-20 — 1,407,321,425 tokens grok-4.7: 523,536,485 grok-4-20-non-reasoning: 440,541,950 grok-4.6: 201,011,855 grok-4-1-fast-non-reasoning: 137,106,230 grok-4-1-fast-reasoning: 51,578,560 grok-4-20-reasoning: 23,024,675 grok-4.3: 21,879,555 grok-4.5: 8,642,115
  • grok-4.7
  • grok-4-20-non-reasoning
  • grok-4-1-fast-non-reasoning
  • grok-4.6
  • grok-4.3
  • grok-4.5
  • grok-4-1-fast-reasoning
  • grok-4-20-reasoning
  • 1 more model

Which models that traffic went to

  1. Grok 4.732.4%10.9B
  2. grok-4-20-non-reasoning26.9%9B
  3. grok-4-1-fast-non-reasoning16.1%5.4B
  4. Grok 4.612.3%4.1B
  5. Grok 4.34.5%1.5B
  6. Grok 4.53.9%1.3B
  7. Grok 4.1 Fast (reasoning)3.1%1B
  8. Grok 4 20 (reasoning)0.8%266M
  9. 1 more model<0.1%1.7M

Share of 33.5B tokens. 16 models with traffic report no token counts and cannot be ranked here, including grok-imagine-image-2.0 and grok-4.20-multi-agent-beta-0309 — 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 28 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 28 Grok Models

Open in model list
Grok 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
grok-4.20-beta-0309-non-reasoningTakes text, vision, returns text.2M—$2$6/M$1/M89 tok/s0.91 s
grok-4.20-beta-0309-reasoningTakes text, vision, returns text.2M30K$2$6/M$1/M74 tok/s1.69 s
grok-4.20-multi-agent-beta-0309Takes text, vision, returns text.2M—$2$6/M$0.2/M43 tok/s4.26 s
grok-4-1-fast-non-reasoningTakes text, vision, returns text.1M—$0.2$0.5/M—86 tok/s0.67 s
grok-4-1-fast-reasoningTakes text, vision, returns text.1M—$0.2$0.5/M—86 tok/s2.83 s
grok-4-fast-non-reasoningTakes text, vision, returns text.1M30K$0.2$0.5/M$0.05/M137 tok/s2.70 s
grok-4-fast-reasoningTakes text, vision, returns text.1M30K$0.2$0.5/M$0.05/M137 tok/s2.70 s
grok-4.3Takes text, vision, returns text.1M30K$1.25$2.5/M—70 tok/s0.41 s
grok-4-20-non-reasoningTakes text, vision, returns text.1M—$2$6/M—168 tok/s0.54 s
grok-4-20-reasoningTakes text, vision, returns text.1M—$2$6/M—94 tok/s0.49 s
grok-4.20-multi-agent-0309Takes text, vision, returns text.1M—$2$6/M$0.2/M43 tok/s4.26 s
grok-4.5Takes text, vision, returns text.500K—$2$6/M$0.5/M37 tok/s2.48 s
grok-4.6Takes text, vision, returns text.500K—$2$6/M$0.5/M23 tok/s3.23 s
grok-4.7Takes text, vision, returns text.500K—$2$6/M$0.5/M21 tok/s5.54 s
grok-build-0.1Takes text, vision, returns text.256K—$1$2/M$0.2/M65 tok/s0.56 s
grok-code-fast-1Takes text, vision, returns text.256K10K$1$2/M$0.2/M87 tok/s1.26 s
grok-4Takes text, vision, returns text.256K64K$3.3$16.5/M$0.825/M54 tok/s2.70 s
grok-3-miniTakes , returns text.——$0.3$0.501/M———
grok-3-mini-betaTakes , returns text.——$0.33$0.5511/M———
grok-3-mini-fast-betaTakes , returns text.——$0.33$2.2001/M———
grok-2-1212Takes , returns text.——$1.8$9/M———
grok-2-vision-1212Takes text, vision, returns text.——$1.8$9/M———
grok-3Takes , returns text.——$3$15/M———
grok-3-betaTakes , returns text.——$3$15/M———
grok-3-fastTakes , returns text.——$5.5$27.5/M———
grok-3-fast-betaTakes , returns text.——$5.5$27.5/M———
grok-vision-betaTakes text, vision, returns text.——$5.6$16.8/M———
grok-imagine-image-2.0Takes text, vision, returns vision.——from $0.044 / 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.

Grok on AIHubMix

Which Grok model should I start with?

grok-4-1-fast-non-reasoning at $0.2/M input — the cheapest entry here that declares tool calling, and it carries a 1M context. Move up to grok-vision-beta when answer quality matters more than cost, or to grok-4.20-beta-0309-non-reasoning for long-form reasoning.

Which of these models reason before answering?

14 of the 28 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-), 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 grok-4.20-multi-agent-0309 bills cache hits at 10% of the input rate and grok-4.20-multi-agent-beta-0309 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 Grok 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 Grok in one line

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