Anthropic Models

35 modelsGeneral models from $1.1/M inputUp to 1M context

Usage

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

Tokens

541B

Requests

4.5M

Models in use

34 of 35

Tokens per day, stacked by model

013.1B26.2B10-2410-3111-0711-1411-212026-10-24 — 12,074,405,394 tokens claude-opus-5-5: 7,129,996,827 claude-sonnet-5-5: 3,732,306,203 claude-haiku-5-5: 432,625,070 claude-sonnet-5: 229,504,417 claude-opus-5: 226,349,675 claude-opus-4-8: 140,461,162 13 more models: 121,014,054 claude-sonnet-4-6: 62,147,9862026-10-25 — 11,682,808,530 tokens claude-opus-5-5: 7,522,640,427 claude-sonnet-5-5: 3,138,468,859 claude-opus-5: 302,046,007 claude-haiku-5-5: 197,263,306 claude-sonnet-5: 178,483,407 claude-opus-4-8: 163,863,459 13 more models: 144,561,490 claude-sonnet-4-6: 35,481,5752026-10-26 — 25,968,353,597 tokens claude-opus-5-5: 14,063,212,688 claude-sonnet-5-5: 8,313,759,078 claude-opus-5: 1,157,229,104 claude-haiku-5-5: 776,031,521 claude-sonnet-5: 581,347,990 13 more models: 440,669,806 claude-opus-4-8: 429,838,673 claude-sonnet-4-6: 206,264,7372026-10-27 — 22,904,098,181 tokens claude-opus-5-5: 11,147,315,397 claude-sonnet-5-5: 6,927,421,639 claude-opus-5: 1,322,781,439 claude-haiku-5-5: 1,117,094,690 claude-opus-4-8: 974,439,432 claude-sonnet-5: 650,944,386 13 more models: 449,974,689 claude-sonnet-4-6: 314,126,5092026-10-28 — 26,207,410,222 tokens claude-opus-5-5: 14,968,935,135 claude-sonnet-5-5: 7,556,313,393 claude-opus-5: 1,217,173,046 claude-haiku-5-5: 884,041,068 claude-sonnet-5: 552,172,679 claude-sonnet-4-6: 374,456,238 claude-opus-4-8: 364,770,793 13 more models: 289,547,8702026-10-29 — 26,025,927,867 tokens claude-opus-5-5: 13,885,731,219 claude-sonnet-5-5: 6,029,192,389 claude-haiku-5-5: 1,733,076,816 claude-opus-5: 1,501,150,138 claude-sonnet-5: 1,281,961,518 claude-opus-4-8: 821,938,341 13 more models: 584,536,318 claude-sonnet-4-6: 188,341,1282026-10-30 — 19,368,665,633 tokens claude-opus-5-5: 10,282,857,831 claude-sonnet-5-5: 4,408,526,223 claude-opus-5: 1,240,891,446 claude-haiku-5-5: 938,894,737 claude-opus-4-8: 920,879,500 claude-sonnet-5: 579,534,231 claude-sonnet-4-6: 517,632,724 13 more models: 479,448,9412026-10-31 — 6,275,142,296 tokens claude-opus-5-5: 2,553,877,701 claude-sonnet-5-5: 949,403,036 claude-opus-5: 664,530,113 claude-sonnet-4-6: 565,400,991 claude-haiku-5-5: 501,694,872 claude-sonnet-5: 399,129,439 claude-opus-4-8: 398,761,186 13 more models: 242,344,9582026-11-01 — 6,979,223,754 tokens claude-opus-5-5: 2,483,796,846 claude-opus-5: 1,853,031,384 claude-sonnet-5-5: 1,083,506,613 claude-sonnet-4-6: 430,891,553 claude-haiku-5-5: 351,834,555 claude-sonnet-5: 312,831,467 claude-opus-4-8: 239,864,771 13 more models: 223,466,5652026-11-02 — 12,835,131,930 tokens claude-opus-5-5: 6,747,512,553 claude-sonnet-5-5: 1,978,802,789 claude-opus-5: 1,380,175,573 13 more models: 737,002,924 claude-opus-4-8: 623,553,128 claude-sonnet-5: 534,758,588 claude-haiku-5-5: 500,808,756 claude-sonnet-4-6: 332,517,6192026-11-03 — 22,607,773,686 tokens claude-opus-5-5: 13,537,986,482 claude-sonnet-5-5: 4,008,298,508 claude-haiku-5-5: 1,723,992,694 claude-opus-5: 1,493,567,092 13 more models: 761,532,919 claude-opus-4-8: 387,734,741 claude-sonnet-4-6: 367,616,767 claude-sonnet-5: 327,044,4832026-11-04 — 22,899,067,568 tokens claude-opus-5-5: 13,338,017,231 claude-sonnet-5-5: 4,068,193,456 claude-haiku-5-5: 1,874,350,818 claude-opus-5: 1,824,337,847 13 more models: 852,412,159 claude-opus-4-8: 339,241,333 claude-sonnet-5: 317,840,787 claude-sonnet-4-6: 284,673,9372026-11-05 — 22,263,505,953 tokens claude-opus-5-5: 13,885,576,986 claude-sonnet-5-5: 3,159,773,008 claude-opus-5: 2,147,489,355 claude-haiku-5-5: 1,168,871,111 13 more models: 655,206,245 claude-opus-4-8: 472,473,489 claude-sonnet-5: 420,453,459 claude-sonnet-4-6: 353,662,3002026-11-06 — 23,267,665,368 tokens claude-opus-5-5: 14,844,270,312 claude-sonnet-5-5: 3,369,273,767 claude-haiku-5-5: 1,657,603,773 claude-opus-5: 1,227,724,479 claude-opus-4-8: 859,477,615 13 more models: 784,103,163 claude-sonnet-5: 424,130,152 claude-sonnet-4-6: 101,082,1072026-11-07 — 12,397,240,187 tokens claude-opus-5-5: 8,600,134,599 claude-sonnet-5-5: 1,300,915,101 claude-haiku-5-5: 1,278,008,489 claude-opus-5: 491,828,431 13 more models: 354,790,969 claude-sonnet-5: 185,529,907 claude-sonnet-4-6: 100,744,528 claude-opus-4-8: 85,288,1632026-11-08 — 10,475,862,064 tokens claude-opus-5-5: 6,462,765,842 claude-sonnet-5-5: 2,275,660,791 claude-haiku-5-5: 689,896,788 claude-opus-5: 570,838,220 claude-sonnet-5: 223,452,030 13 more models: 194,136,609 claude-sonnet-4-6: 43,906,490 claude-opus-4-8: 15,205,2942026-11-09 — 22,292,785,488 tokens claude-opus-5-5: 12,968,940,912 claude-sonnet-5-5: 4,056,030,768 claude-opus-5: 1,404,260,966 claude-haiku-5-5: 1,286,005,902 claude-sonnet-5: 1,008,043,548 13 more models: 683,312,572 claude-opus-4-8: 640,930,173 claude-sonnet-4-6: 245,260,6472026-11-10 — 24,186,860,345 tokens claude-opus-5-5: 15,313,273,895 claude-sonnet-5-5: 3,295,797,727 claude-opus-5: 1,723,570,731 claude-haiku-5-5: 1,101,482,074 claude-opus-4-8: 901,090,580 claude-sonnet-5: 714,088,137 13 more models: 656,175,992 claude-sonnet-4-6: 381,935,728 claude-fable-5-2: 99,445,4812026-11-11 — 21,922,065,385 tokens claude-opus-5-5: 14,480,943,498 claude-sonnet-5-5: 2,213,243,640 claude-haiku-5-5: 1,555,591,341 claude-opus-5: 1,474,649,942 claude-sonnet-5: 759,198,491 13 more models: 530,115,131 claude-opus-4-8: 325,817,689 claude-sonnet-4-6: 318,984,428 claude-fable-5-2: 263,521,2252026-11-12 — 23,821,650,705 tokens claude-opus-5-5: 12,849,972,015 claude-haiku-5-5: 3,665,888,094 claude-sonnet-5-5: 3,378,299,379 claude-sonnet-5: 937,899,153 claude-opus-5: 890,296,413 claude-fable-5-2: 589,964,401 13 more models: 559,129,765 claude-sonnet-4-6: 519,816,254 claude-opus-4-8: 430,385,2312026-11-13 — 26,066,002,274 tokens claude-opus-5-5: 12,602,470,060 claude-sonnet-5-5: 5,109,158,855 claude-haiku-5-5: 4,260,820,576 claude-opus-5: 1,304,996,512 claude-sonnet-5: 862,762,104 claude-sonnet-4-6: 578,100,705 claude-fable-5-2: 558,920,242 13 more models: 446,484,301 claude-opus-4-8: 342,288,9192026-11-14 — 17,366,206,474 tokens claude-opus-5-5: 8,048,802,961 claude-sonnet-5-5: 6,668,185,174 claude-haiku-5-5: 738,631,696 claude-fable-5-2: 721,298,921 claude-sonnet-5: 504,367,072 claude-opus-5: 234,933,006 claude-sonnet-4-6: 230,540,435 13 more models: 158,491,341 claude-opus-4-8: 60,955,8682026-11-15 — 8,033,380,918 tokens claude-opus-5-5: 4,847,348,486 claude-sonnet-5-5: 1,099,434,426 claude-haiku-5-5: 727,645,961 claude-fable-5-2: 505,311,146 claude-sonnet-5: 501,239,591 13 more models: 132,770,775 claude-sonnet-4-6: 114,815,182 claude-opus-5: 63,571,148 claude-opus-4-8: 41,244,2032026-11-16 — 22,821,283,076 tokens claude-opus-5-5: 12,834,983,588 claude-sonnet-5-5: 3,187,637,940 claude-haiku-5-5: 1,989,854,210 claude-fable-5-2: 1,591,881,953 claude-sonnet-5: 1,326,349,820 claude-opus-5: 959,297,261 claude-opus-4-8: 422,393,905 13 more models: 311,976,372 claude-sonnet-4-6: 196,908,0272026-11-17 — 17,138,626,644 tokens claude-opus-5-5: 7,932,762,705 claude-sonnet-5-5: 2,464,562,304 claude-haiku-5-5: 2,213,753,904 claude-opus-5: 1,440,348,078 claude-sonnet-5: 1,283,115,934 claude-fable-5-2: 961,277,599 13 more models: 284,097,407 claude-sonnet-4-6: 280,050,912 claude-opus-4-8: 278,657,8012026-11-18 — 20,718,267,007 tokens claude-opus-5-5: 10,246,053,658 claude-haiku-5-5: 3,386,647,766 claude-sonnet-5-5: 2,698,390,388 claude-sonnet-5: 2,032,531,688 claude-opus-5: 1,120,409,252 claude-sonnet-4-6: 401,170,001 claude-opus-4-8: 312,402,636 claude-fable-5-2: 278,586,523 13 more models: 242,075,0952026-11-19 — 24,691,163,246 tokens claude-opus-5-5: 13,509,528,833 claude-sonnet-5-5: 3,912,048,568 claude-haiku-5-5: 2,876,311,778 claude-sonnet-5: 1,880,575,197 claude-opus-5: 1,266,417,014 claude-sonnet-4-6: 474,176,564 claude-opus-4-8: 329,836,982 claude-fable-5-2: 290,115,280 13 more models: 152,153,0302026-11-20 — 14,232,758,486 tokens claude-opus-5-5: 6,854,191,328 claude-sonnet-5-5: 2,084,992,809 claude-haiku-5-5: 1,300,763,424 claude-sonnet-5: 1,201,750,900 claude-opus-5: 983,048,398 claude-opus-4-8: 644,392,547 claude-fable-5-2: 601,805,010 claude-sonnet-4-6: 369,059,333 13 more models: 192,754,7372026-11-21 — 6,773,075,416 tokens claude-opus-5-5: 3,278,796,990 claude-sonnet-5-5: 1,186,512,534 claude-haiku-5-5: 946,177,836 claude-sonnet-5: 534,507,822 claude-opus-5: 244,334,621 claude-fable-5-2: 224,512,119 claude-sonnet-4-6: 216,863,482 13 more models: 117,739,891 claude-opus-4-8: 23,630,1212026-11-22 — 6,773,365,086 tokens claude-opus-5-5: 2,424,852,633 claude-sonnet-5-5: 965,475,243 claude-sonnet-4-6: 945,299,289 claude-haiku-5-5: 701,651,652 claude-sonnet-5: 678,193,695 claude-fable-5-2: 519,349,333 claude-opus-5: 408,242,206 13 more models: 116,351,770 claude-opus-4-8: 13,949,265
  • claude-opus-5-5
  • claude-sonnet-5-5
  • claude-haiku-5-5
  • claude-opus-5
  • claude-sonnet-5
  • claude-opus-4-8
  • claude-sonnet-4-6
  • claude-fable-5-2
  • 13 more models

Which models that traffic went to

  1. Claude Opus 5.555.4%300B
  2. Claude Sonnet 5.519.3%105B
  3. Claude Haiku 5.57.9%42.6B
  4. Claude Opus 55.9%32.1B
  5. Claude Sonnet 54.0%21.4B
  6. Claude Opus 4.82.2%12B
  7. Claude Sonnet 4.61.8%9.6B
  8. Claude Fable 5.21.3%7.2B
  9. 13 more models2.2%11.9B

Share of 541B tokens. 13 models with traffic report no token counts and cannot be ranked here, including claude-opus-4-1 and claude-3-haiku-20240307 — 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 35 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 35 Anthropic Models

Open in model list
Anthropic 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
claude-haiku-5-5Takes text, vision, returns text.1M128K$0.1$0.5/M$0.01/M$0.125/M187 tok/s0.60 s
claude-sonnet-5Takes text, vision, PDF, returns text.1M128K$2$10/M$0.2/M$2.5/M7839 tok/s0.80 s
claude-sonnet-5-5Takes text, vision, PDF, returns text.1M128K$2$10/M$0.1/M$2.5/M126 tok/s0.67 s
claude-sonnet-4-6Takes text, vision, PDF, returns text.1M128K$3$15/M$0.3/M$3.75/M108 tok/s0.70 s
claude-sonnet-4-6-thinkTakes text, vision, PDF, returns text.1M128K$3$15/M$0.3/M$3.75/M136 tok/s1.00 s
claude-opus-5-5Takes text, vision, PDF, returns text.1M128K$4$20/M$0.2/M$5/M100 tok/s0.95 s
claude-opus-4-6Takes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M60 tok/s1.21 s
claude-opus-4-6-thinkTakes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M66 tok/s1.27 s
claude-opus-4-7Takes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M86 tok/s0.61 s
claude-opus-4-7-thinkTakes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M123 tok/s0.81 s
claude-opus-4-8Takes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M92 tok/s0.60 s
claude-opus-4-8-thinkTakes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M55 tok/s0.84 s
claude-opus-5Takes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M86 tok/s0.45 s
claude-fable-5-2Takes text, vision, PDF, returns text.1M128K$8.8$44/M$0.22/M$11/M92 tok/s1.83 s
claude-fable-5Takes text, vision, PDF, returns text.1M128K$11$55/M$1.1/M$13.75/M68 tok/s1.12 s
claude-fable-5-1Takes text, vision, PDF, returns text.1M128K$11$55/M$0.275/M$13.75/M71 tok/s27.77 s
claude-3-haiku-20240229Takes text, vision, returns text.200K—$0.275$0.275/M————
claude-3-haiku@20240307Takes text, vision, returns text.200K—$0.275$1.375/M————
claude-haiku-4-5Takes text, vision, PDF, returns text.200K64K$1.1$5.5/M$0.11/M$1.375/M153 tok/s0.30 s
claude-3-7-sonnetTakes text, vision, returns text.200K128K$3.3$16.5/M——57 tok/s0.63 s
claude-3-sonnet-20240229Takes text, vision, returns text.200K—$3.3$16.5/M——67 tok/s0.76 s
claude-sonnet-4-5Takes text, vision, PDF, returns text.200K64K$3.3$16.5/M$0.33/M$4.125/M58 tok/s0.86 s
claude-sonnet-4-5-thinkTakes text, vision, PDF, returns text.200K64K$3.3$16.5/M$0.33/M$4.125/M41 tok/s1.52 s
anthropic-opus-4-6Takes text, vision, returns text.200K32K$5$25/M$0.5/M$6.25/M——
claude-opus-4-5Takes text, vision, PDF, returns text.200K64K$5$25/M$0.5/M$6.25/M69 tok/s1.13 s
claude-opus-4-5-thinkTakes text, vision, PDF, returns text.200K64K$5$25/M$0.5/M$6.25/M33 tok/s1.86 s
claude-opus-4-1Takes text, vision, returns text.200K32K$16.5$82.5/M——41 tok/s1.69 s
claude-3-haiku-20240307Takes text, vision, returns text.——$0.275$1.375/M——48 tok/s1.22 s
claude-instant-1.2Takes , returns text.——$0.88$3.96/M————
claude-instant-1Takes , returns text.——$1.793$1.793/M————
claude-2Takes , returns text.——$8.8$8.8/M————
claude-2.0Takes , returns text.——$8.8$39.6/M————
claude-2.1Takes , returns text.——$8.8$39.6/M————
claude-3-opus-20240229Takes , returns text.——$16.5$82.5/M————
claude-3-opus@20240229Takes , returns text.——$16.5$82.5/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.

Anthropic on AIHubMix

Which Anthropic model should I start with?

claude-haiku-4-5 at $1.1/M input — the cheapest entry here that declares tool calling, and it carries a 200K context. Move up to claude-opus-4-1 when answer quality matters more than cost, or to claude-sonnet-5 for long-form reasoning.

Which of these models reason before answering?

20 of the 35 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 claude-fable-5-1 bills cache hits at 2.5% of the input rate and claude-fable-5-2 bills cache hits at 2.5% 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 Anthropic 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 Anthropic in one line

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