Anthropic Models

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

Usage

Last 30 days · 2026-10-02 to 2026-10-31

Tokens

432B

Requests

4M

Models in use

33 of 34

Tokens per day, stacked by model

013.1B26.2B10-0210-0910-1610-2310-302026-10-02 — 2,217,955,236 tokens claude-opus-5-5: 1,086,640,064 claude-opus-5: 376,286,645 claude-sonnet-5-5: 262,949,473 claude-sonnet-4-6: 232,944,444 13 more models: 127,523,141 claude-opus-4-8: 82,361,688 claude-sonnet-5: 41,254,020 claude-fable-5: 7,995,7612026-10-03 — 2,962,491,525 tokens claude-opus-5-5: 1,800,728,397 claude-sonnet-4-6: 430,364,524 claude-sonnet-5-5: 277,353,529 13 more models: 263,048,669 claude-opus-5: 141,288,417 claude-sonnet-5: 30,080,367 claude-opus-4-8: 12,049,812 claude-fable-5: 7,577,8102026-10-04 — 4,311,730,547 tokens claude-opus-5-5: 2,829,899,243 claude-sonnet-4-6: 518,030,992 claude-sonnet-5-5: 427,053,678 13 more models: 283,665,540 claude-opus-5: 191,157,814 claude-sonnet-5: 34,046,114 claude-fable-5: 15,079,292 claude-opus-4-8: 12,797,8742026-10-05 — 5,621,189,279 tokens claude-opus-5-5: 4,044,136,125 claude-sonnet-4-6: 542,858,158 claude-sonnet-5-5: 387,846,166 13 more models: 255,144,409 claude-opus-5: 197,135,462 claude-sonnet-5: 145,466,434 claude-opus-4-8: 38,203,170 claude-fable-5: 10,399,3552026-10-06 — 6,415,369,327 tokens claude-opus-5-5: 4,213,353,630 claude-sonnet-5-5: 911,887,552 claude-sonnet-4-6: 464,252,831 claude-sonnet-5: 250,992,955 claude-opus-5: 248,740,126 13 more models: 156,342,802 claude-fable-5: 98,188,063 claude-opus-4-8: 71,611,3682026-10-07 — 6,079,627,195 tokens claude-opus-5-5: 4,312,825,408 claude-sonnet-5-5: 682,935,300 claude-sonnet-4-6: 443,254,130 claude-sonnet-5: 237,642,547 13 more models: 217,821,160 claude-opus-5: 128,000,430 claude-opus-4-8: 55,237,299 claude-fable-5: 1,910,9212026-10-08 — 11,402,729,766 tokens claude-opus-5-5: 5,694,872,935 claude-opus-5: 2,013,203,386 claude-sonnet-5-5: 1,704,427,973 claude-sonnet-4-6: 688,448,788 claude-sonnet-5: 512,392,941 13 more models: 381,419,456 claude-opus-4-8: 227,687,814 claude-haiku-5-5: 166,389,346 claude-fable-5: 13,887,1272026-10-09 — 12,729,629,143 tokens claude-opus-5-5: 6,118,303,965 claude-sonnet-5-5: 2,481,458,780 claude-opus-5: 2,002,676,481 claude-sonnet-4-6: 564,548,179 claude-sonnet-5: 545,595,285 13 more models: 452,477,327 claude-haiku-5-5: 355,168,217 claude-opus-4-8: 178,592,882 claude-fable-5: 30,808,0272026-10-10 — 12,700,463,657 tokens claude-opus-5-5: 8,146,848,451 claude-sonnet-5-5: 1,773,662,397 claude-sonnet-4-6: 678,224,702 claude-sonnet-5: 642,516,020 claude-haiku-5-5: 441,234,380 claude-opus-5: 439,924,232 13 more models: 381,222,574 claude-opus-4-8: 110,883,553 claude-fable-5: 85,947,3482026-10-11 — 6,903,248,865 tokens claude-opus-5-5: 4,317,926,992 claude-sonnet-5-5: 927,211,884 claude-sonnet-4-6: 510,924,771 claude-opus-5: 325,700,668 claude-haiku-5-5: 264,205,230 claude-fable-5: 213,804,627 claude-sonnet-5: 187,393,884 13 more models: 107,267,654 claude-opus-4-8: 48,813,1552026-10-12 — 15,234,701,178 tokens claude-opus-5-5: 6,774,580,046 claude-opus-5: 3,187,071,624 claude-sonnet-5-5: 2,534,101,831 claude-haiku-5-5: 824,380,006 claude-sonnet-4-6: 786,828,670 claude-sonnet-5: 492,408,145 13 more models: 362,667,970 claude-opus-4-8: 200,259,589 claude-fable-5: 72,403,2972026-10-13 — 16,737,715,670 tokens claude-opus-5-5: 7,137,493,505 claude-sonnet-5-5: 2,820,786,997 claude-opus-5: 2,184,561,979 claude-haiku-5-5: 1,712,575,921 claude-sonnet-5: 786,501,193 claude-sonnet-4-6: 726,676,268 claude-fable-5: 644,716,424 13 more models: 469,154,464 claude-opus-4-8: 255,248,9192026-10-14 — 17,530,477,886 tokens claude-opus-5-5: 8,066,224,484 claude-sonnet-5-5: 3,156,659,854 claude-opus-5: 2,992,666,710 claude-sonnet-5: 965,510,905 claude-haiku-5-5: 741,692,540 claude-sonnet-4-6: 629,860,497 claude-opus-4-8: 410,013,701 13 more models: 330,922,186 claude-fable-5: 236,927,0092026-10-15 — 19,502,011,983 tokens claude-opus-5-5: 8,396,228,904 claude-sonnet-5-5: 4,515,731,100 claude-opus-5: 3,094,184,359 claude-haiku-5-5: 1,029,358,902 claude-sonnet-5: 901,621,715 claude-opus-4-8: 611,378,517 13 more models: 410,171,716 claude-sonnet-4-6: 366,947,426 claude-fable-5: 176,389,3442026-10-16 — 20,006,505,303 tokens claude-opus-5-5: 8,632,733,756 claude-sonnet-5-5: 6,258,024,045 claude-opus-5: 1,425,335,439 claude-haiku-5-5: 1,064,089,233 claude-sonnet-5: 1,015,703,121 claude-opus-4-8: 843,714,138 13 more models: 332,928,003 claude-sonnet-4-6: 313,554,752 claude-fable-5: 120,422,8162026-10-17 — 8,601,810,461 tokens claude-opus-5-5: 5,556,975,618 claude-sonnet-5-5: 937,854,097 claude-opus-5: 652,287,701 claude-sonnet-5: 570,197,564 claude-sonnet-4-6: 353,816,587 claude-opus-4-8: 256,909,001 13 more models: 139,121,518 claude-haiku-5-5: 107,016,588 claude-fable-5: 27,631,7872026-10-18 — 7,506,001,196 tokens claude-opus-5-5: 5,875,003,702 claude-sonnet-5-5: 570,206,504 claude-sonnet-5: 299,626,182 claude-opus-5: 228,540,773 13 more models: 185,506,948 claude-opus-4-8: 145,825,219 claude-haiku-5-5: 138,959,097 claude-sonnet-4-6: 61,476,557 claude-fable-5: 856,2142026-10-19 — 15,474,206,589 tokens claude-opus-5-5: 7,934,744,202 claude-sonnet-5-5: 3,303,903,172 claude-opus-5: 1,287,165,078 claude-haiku-5-5: 1,116,827,589 claude-sonnet-5: 842,308,530 claude-opus-4-8: 528,821,084 claude-sonnet-4-6: 264,801,432 13 more models: 191,618,529 claude-fable-5: 4,016,9732026-10-20 — 23,079,817,468 tokens claude-opus-5-5: 12,875,131,263 claude-sonnet-5-5: 5,054,068,783 claude-haiku-5-5: 1,446,829,635 claude-sonnet-5: 1,409,683,851 claude-opus-5: 1,367,905,173 13 more models: 377,352,953 claude-opus-4-8: 343,439,295 claude-sonnet-4-6: 171,555,075 claude-fable-5: 33,851,4402026-10-21 — 23,418,046,674 tokens claude-opus-5-5: 15,463,436,164 claude-sonnet-5-5: 3,182,294,155 claude-opus-5: 1,731,820,002 claude-sonnet-5: 1,227,041,803 claude-haiku-5-5: 689,168,398 claude-opus-4-8: 492,515,519 13 more models: 331,392,887 claude-sonnet-4-6: 244,753,010 claude-fable-5: 55,624,7362026-10-22 — 22,258,116,666 tokens claude-opus-5-5: 13,076,871,263 claude-sonnet-5-5: 4,219,358,857 claude-haiku-5-5: 1,697,260,022 claude-opus-5: 1,233,596,361 claude-sonnet-5: 822,930,173 claude-sonnet-4-6: 490,887,376 13 more models: 387,216,065 claude-opus-4-8: 313,071,760 claude-fable-5: 16,924,7892026-10-23 — 20,883,725,250 tokens claude-opus-5-5: 11,949,605,976 claude-sonnet-5-5: 4,835,471,037 claude-opus-5: 1,085,146,249 claude-haiku-5-5: 901,550,098 claude-sonnet-5: 790,540,171 claude-opus-4-8: 553,133,275 13 more models: 382,847,456 claude-sonnet-4-6: 258,496,394 claude-fable-5: 126,934,5942026-10-24 — 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: 111,987,907 claude-sonnet-4-6: 62,147,986 claude-fable-5: 9,026,1472026-10-25 — 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: 120,436,524 claude-sonnet-4-6: 35,481,575 claude-fable-5: 24,124,9662026-10-26 — 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 claude-opus-4-8: 429,838,673 13 more models: 333,386,643 claude-sonnet-4-6: 206,264,737 claude-fable-5: 107,283,1632026-10-27 — 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 claude-sonnet-4-6: 314,126,509 13 more models: 304,422,049 claude-fable-5: 145,552,6402026-10-28 — 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: 247,524,872 claude-fable-5: 42,022,9982026-10-29 — 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: 454,161,656 claude-sonnet-4-6: 188,341,128 claude-fable-5: 130,374,6622026-10-30 — 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: 466,503,663 claude-fable-5: 12,945,2782026-10-31 — 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: 210,185,310 claude-fable-5: 32,159,648
  • claude-opus-5-5
  • claude-sonnet-5-5
  • claude-opus-5
  • claude-haiku-5-5
  • claude-sonnet-5
  • claude-sonnet-4-6
  • claude-opus-4-8
  • claude-fable-5
  • 13 more models

Which models that traffic went to

  1. Claude Opus 5.554.6%236B
  2. Claude Sonnet 5.521.4%92.3B
  3. Claude Opus 57.9%34.2B
  4. Claude Haiku 5.54.5%19.3B
  5. Claude Sonnet 54.0%17.2B
  6. Claude Sonnet 4.62.8%12B
  7. Claude Opus 4.82.3%10B
  8. Claude Fable 50.6%2.5B
  9. 13 more models2.0%8.8B

Share of 432B tokens. 12 models with traffic report no token counts and cannot be ranked here, including claude-3-haiku-20240307 and claude-3-sonnet-20240229 — 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 34 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 34 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/s1.03 s
claude-sonnet-5-5Takes text, vision, PDF, returns text.1M128K$2$10/M$0.1/M$2.5/M108 tok/s2.01 s
claude-sonnet-4-6Takes text, vision, PDF, returns text.1M128K$3$15/M$0.3/M$3.75/M108 tok/s0.75 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/s1.29 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/M158 tok/s0.65 s
claude-opus-4-8Takes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M92 tok/s0.65 s
claude-opus-4-8-thinkTakes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M72 tok/s1.11 s
claude-opus-5Takes text, vision, PDF, returns text.1M128K$5$25/M$0.5/M$6.25/M84 tok/s1.08 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/M65 tok/s4.40 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/s0.41 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/M53 tok/s1.29 s
claude-sonnet-4-5-thinkTakes text, vision, PDF, returns text.200K64K$3.3$16.5/M$0.33/M$4.125/M41 tok/s2.62 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/M46 tok/s2.25 s
claude-opus-4-5-thinkTakes text, vision, PDF, returns text.200K64K$5$25/M$0.5/M$6.25/M44 tok/s1.67 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.

Common Comparisons

anthropic-opus-4-6 vs claude-2anthropic-opus-4-6 vs claude-2.0anthropic-opus-4-6 vs claude-2.1anthropic-opus-4-6 vs qwen3.8-max-previewanthropic-opus-4-6 vs kimi-k3

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 34 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-opus-5-5 bills cache hits at 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.

Other Model Authors

See all model authors →
Qwen
154 modelsOpenAI
144 modelsGoogle
90 modelsZ.AI
72 modelsLlama
53 models

Start calling Anthropic in one line

One key, one endpoint, 941 models across 46 model authors.

Get API keyRead the docs

© 2023 - 2026 AIHubMix, LLC

Product

Developer

Company

Terms & Policies