AIHubMixAIHubMix

Anthropic Models

30 modelsGeneral models from $1.10/M inputUp to 1M context

Usage

Last 30 days · 2026-07-13 to 2026-08-11

Tokens

253B

Requests

2.8M

Models in use

23 of 30

Tokens per day

06.1B12.2B07-1307-2007-2708-0308-102026-07-13 — 10,012,425,648 tokens2026-07-14 — 10,764,923,017 tokens2026-07-15 — 10,607,692,921 tokens2026-07-16 — 10,094,072,351 tokens2026-07-17 — 9,079,561,138 tokens2026-07-18 — 2,982,628,324 tokens2026-07-19 — 3,001,395,818 tokens2026-07-20 — 8,490,698,140 tokens2026-07-21 — 10,517,531,281 tokens2026-07-22 — 10,327,668,352 tokens2026-07-23 — 9,947,368,476 tokens2026-07-24 — 8,839,123,680 tokens2026-07-25 — 3,191,136,533 tokens2026-07-26 — 2,452,191,370 tokens2026-07-27 — 9,757,297,300 tokens2026-07-28 — 11,993,923,559 tokens2026-07-29 — 10,843,211,314 tokens2026-07-30 — 11,306,888,747 tokens2026-07-31 — 9,986,982,087 tokens2026-08-01 — 3,641,399,553 tokens2026-08-02 — 2,897,942,326 tokens2026-08-03 — 12,210,503,539 tokens2026-08-04 — 10,095,637,176 tokens2026-08-05 — 11,296,684,597 tokens2026-08-06 — 9,629,607,686 tokens2026-08-07 — 9,090,602,774 tokens2026-08-08 — 4,210,830,595 tokens2026-08-09 — 4,193,124,676 tokens2026-08-10 — 9,833,689,762 tokens2026-08-11 — 11,238,689,510 tokens

Which models that traffic went to

  1. claude-opus-4-829.5%74.6B
  2. claude-sonnet-526.9%67.8B
  3. claude-opus-518.4%46.6B
  4. claude-sonnet-4-68.3%21.1B
  5. claude-fable-55.9%14.8B
  6. claude-opus-4-74.7%11.8B
  7. claude-opus-4-63.7%9.4B
  8. claude-haiku-4-50.8%2.1B
  9. 9 more models1.7%4.2B

Share of 253B tokens. 6 models with traffic report no token counts and cannot be ranked here, including claude-3-7-sonnet 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 30 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 30 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-sonnet-5Takes text, vision, returns text.1M128K$2.00$10.00/M$0.20/M$2.50/M91 tok/s1.55 s
claude-sonnet-4-6Takes text, vision, returns text.1M64K$3.00$15.00/M$0.30/M$3.75/M61 tok/s0.88 s
claude-sonnet-4-5Takes text, vision, returns text.1M64K$3.30$16.50/M$0.33/M$4.13/M55 tok/s1.61 s
claude-sonnet-4-5-thinkTakes text, vision, returns text.1M64K$3.30$16.50/M$0.33/M$4.13/M——
claude-opus-4-8Takes text, vision, returns text.1M32K$5.00$25.00/M$0.50/M$6.25/M62 tok/s0.93 s
claude-opus-5Takes text, vision, returns text.1M128K$5.00$25.00/M$0.50/M$6.25/M67 tok/s1.42 s
claude-fable-5Takes text, vision, returns text.1M128K$11.00$55.00/M$1.10/M$13.75/M51 tok/s5.34 s
claude-3-haiku-20240229Takes text, vision, returns text.200K—$0.28$0.28/M——67 tok/s0.80 s
claude-3-haiku@20240307Takes text, vision, returns text.200K—$0.28$1.38/M——67 tok/s0.80 s
claude-haiku-4-5Takes text, vision, returns text.200K131K$1.10$5.50/M$0.11/M$1.38/M72 tok/s0.67 s
claude-sonnet-4-6-thinkTakes text, vision, returns text.200K32K$3.00$15.00/M$0.30/M$3.75/M68 tok/s1.18 s
claude-3-7-sonnetTakes text, vision, returns text.200K128K$3.30$16.50/M——57 tok/s0.63 s
claude-3-sonnet-20240229Takes text, vision, returns text.200K—$3.30$16.50/M——67 tok/s0.76 s
anthropic-opus-4-6Takes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M40 tok/s3.07 s
claude-opus-4-5Takes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M43 tok/s1.78 s
claude-opus-4-5-thinkTakes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M——
claude-opus-4-6Takes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M43 tok/s1.98 s
claude-opus-4-6-thinkTakes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M42 tok/s1.74 s
claude-opus-4-7Takes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M68 tok/s2.10 s
claude-opus-4-7-thinkTakes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M80 tok/s3.53 s
claude-opus-4-8-thinkTakes text, vision, returns text.200K32K$5.00$25.00/M$0.50/M$6.25/M52 tok/s5.72 s
claude-opus-4-1Takes text, vision, returns text.200K32K$16.50$82.50/M——41 tok/s1.69 s
claude-3-haiku-20240307Takes text, vision, returns text.——$0.28$1.38/M——67 tok/s0.80 s
claude-instant-1.2——$0.88$3.96/M————
claude-instant-1——$1.79$1.79/M————
claude-2——$8.80$8.80/M————
claude-2.0——$8.80$39.60/M————
claude-2.1——$8.80$39.60/M————
claude-3-opus-20240229——$16.50$82.50/M————
claude-3-opus@20240229——$16.50$82.50/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-3-7-sonnetanthropic-opus-4-6 vs claude-3-haiku-20240229anthropic-opus-4-6 vs claude-3-haiku-20240307anthropic-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 $1.10/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?

19 of the 30 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 anthropic-opus-4-6 bills cache hits at 10% of the input rate and claude-fable-5 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 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 Providers

Qwen
140 modelsOpenAI
132 modelsGoogle
81 modelsZ.AI
64 modelsLlama
52 models

Start calling Anthropic in one line

One key, one endpoint, 844 models across 35 providers.

Get API keyRead the docs
AIHubMix

© 2023 - 2026 AIHubMix, LLC

Product

Company

Developer

Connect