Cohere Models

21 modelsGeneral models free to startUp to 256K context

Usage

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

Tokens

1B

Requests

51.9K

Models in use

18 of 21

Tokens per day, stacked by model

0212M424M10-2210-2911-0511-1211-192026-10-22 — 109,820 tokens command-a-03-2025: 69,770 north-mini-code-free: 34,195 command-nightly: 5,550 embed-v-4-0: 3052026-10-23 — 312,010,330 tokens cohere-rerank-v5-fast: 310,086,080 cohere-rerank-v5-pro: 1,329,545 north-mini-code-free: 490,940 command-a-03-2025: 82,515 embed-v-4-0: 15,990 command-nightly: 5,120 cohere-command-a: 1402026-10-24 — 15,051,155 tokens cohere-rerank-v5-fast: 14,959,930 command-a-03-2025: 84,900 north-mini-code-free: 6,3252026-10-25 — 1,218,715 tokens embed-v-4-0: 811,530 north-mini-code-free: 321,800 command-a-03-2025: 79,835 command-nightly: 5,5502026-10-26 — 1,321,305 tokens cohere-rerank-v5-pro: 630,715 north-mini-code-free: 440,675 embed-v-4-0: 144,515 command-a-03-2025: 100,065 command-nightly: 5,130 cohere-command-a: 2052026-10-27 — 828,045 tokens cohere-rerank-v5-pro: 469,125 north-mini-code-free: 160,475 command-a-03-2025: 102,690 embed-v-4-0: 75,800 command-nightly: 12,850 cohere-command-a: 7,1052026-10-28 — 13,945,955 tokens cohere-rerank-v5-fast: 5,150,000 embed-v-4-0: 5,089,835 cohere-rerank-v5-pro: 3,292,205 north-mini-code-free: 308,755 command-a-03-2025: 99,975 command-nightly: 5,085 cohere-command-a: 1002026-10-29 — 2,838,145 tokens embed-v-4-0: 2,703,880 command-a-03-2025: 92,410 north-mini-code-free: 41,835 cohere-rerank-v5-pro: 202026-10-30 — 377,445 tokens north-mini-code-free: 173,500 embed-v-4-0: 111,315 command-a-03-2025: 90,015 command-nightly: 2,560 cohere-command-a: 552026-10-31 — 35,083,190 tokens cohere-command-a: 32,417,335 command-a-03-2025: 2,599,215 north-mini-code-free: 60,125 embed-v-4-0: 6,5152026-11-01 — 22,101,750 tokens cohere-command-a: 21,377,285 north-mini-code-free: 695,355 embed-v-4-0: 26,565 command-a-03-2025: 2,5452026-11-02 — 10,633,355 tokens north-mini-code-free: 8,851,645 embed-v-4-0: 1,761,210 command-a-03-2025: 20,290 cohere-command-a: 2102026-11-03 — 2,084,695 tokens north-mini-code-free: 1,921,685 embed-v-4-0: 163,0102026-11-04 — 1,852,625 tokens north-mini-code-free: 1,457,990 embed-v-4-0: 331,195 command-a-03-2025: 63,390 cohere-command-a: 502026-11-05 — 714,465 tokens north-mini-code-free: 341,515 embed-v-4-0: 303,500 command-a-03-2025: 65,510 command-nightly: 2,540 cohere-rerank-v5-fast: 1,100 cohere-rerank-v5-pro: 3002026-11-06 — 809,900 tokens north-mini-code-free: 608,315 embed-v-4-0: 145,745 command-a-03-2025: 55,785 cohere-command-a: 552026-11-07 — 1,745,725 tokens north-mini-code-free: 1,532,610 embed-v-4-0: 142,485 command-a-03-2025: 67,960 command-nightly: 2,550 cohere-command-a: 1202026-11-08 — 34,749,205 tokens cohere-rerank-v5-fast: 17,539,920 cohere-rerank-v5-pro: 16,333,745 north-mini-code-free: 631,530 embed-v-4-0: 140,610 command-a-03-2025: 100,730 command-nightly: 2,550 cohere-command-a: 1202026-11-09 — 423,682,375 tokens cohere-rerank-v5-fast: 415,736,705 north-mini-code-free: 7,543,580 embed-v-4-0: 278,485 command-a-03-2025: 105,170 command-nightly: 17,710 cohere-rerank-v5-pro: 415 cohere-command-a: 3102026-11-10 — 1,857,890 tokens north-mini-code-free: 1,719,280 command-a-03-2025: 79,880 embed-v-4-0: 52,355 cohere-rerank-v5-pro: 6,3752026-11-11 — 6,328,640 tokens north-mini-code-free: 5,683,710 embed-v-4-0: 552,070 command-a-03-2025: 84,980 command-nightly: 7,635 cohere-command-a: 2452026-11-12 — 7,413,370 tokens cohere-rerank-v5-fast: 5,870,015 north-mini-code-free: 1,106,185 embed-v-4-0: 364,335 command-a-03-2025: 69,955 command-nightly: 2,560 cohere-rerank-v5-pro: 225 cohere-command-a: 952026-11-13 — 9,870,260 tokens cohere-rerank-v5-fast: 7,669,050 north-mini-code-free: 1,756,100 embed-v-4-0: 424,745 command-a-03-2025: 20,285 cohere-command-a: 802026-11-14 — 1,935,125 tokens north-mini-code-free: 1,729,015 embed-v-4-0: 178,195 command-a-03-2025: 27,9152026-11-15 — 2,830,515 tokens north-mini-code-free: 1,855,705 cohere-rerank-v5-fast: 833,410 embed-v-4-0: 70,630 command-a-03-2025: 68,105 command-nightly: 2,560 cohere-command-a: 55 cohere-rerank-v5-pro: 502026-11-16 — 7,950,875 tokens cohere-rerank-v5-fast: 6,879,675 north-mini-code-free: 853,355 embed-v-4-0: 137,915 command-a-03-2025: 79,890 cohere-command-a: 402026-11-17 — 9,339,035 tokens cohere-rerank-v5-fast: 7,705,230 embed-v-4-0: 1,506,865 command-a-03-2025: 87,590 north-mini-code-free: 39,245 cohere-command-a: 1052026-11-18 — 48,702,300 tokens cohere-rerank-v5-fast: 43,839,215 north-mini-code-free: 4,707,740 embed-v-4-0: 77,930 command-a-03-2025: 77,4152026-11-19 — 35,886,440 tokens cohere-rerank-v5-fast: 35,539,405 embed-v-4-0: 193,185 command-a-03-2025: 79,905 north-mini-code-free: 73,9452026-11-20 — 1,106,965 tokens cohere-rerank-v5-fast: 633,505 north-mini-code-free: 281,610 embed-v-4-0: 106,345 command-a-03-2025: 82,460 command-nightly: 2,560 cohere-rerank-v5-pro: 380 cohere-command-a: 105
  • cohere-rerank-v5-fast
  • cohere-command-a
  • north-mini-code-free
  • cohere-rerank-v5-pro
  • embed-v-4-0
  • command-a-03-2025
  • command-nightly

Which models that traffic went to

  1. Cohere Rerank V5 Fast86.0%872M
  2. Cohere Command A5.3%53.8M
  3. North Mini Code (free)4.5%45.4M
  4. Cohere Rerank V5 Pro2.2%22.1M
  5. Embed V 4.01.6%15.9M
  6. Command A 03 20250.5%4.6M
  7. Command Nightly<0.1%82.5K

Share of 1B tokens. 11 models with traffic report no token counts and cannot be ranked here, including cohere-rerank-v4.0-fast and cohere-rerank-v4.0-pro — 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 21 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 21 Cohere Models

Open in model list
Cohere 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
north-mini-code-freeTakes text, returns text.256K64KFreeFree/M——
cohere-command-aTakes text, returns text.256K8K$2.5$10/M1 tok/s1.52 s
command-a-03-2025Takes text, returns text.256K8K$2.5$10/M41 tok/s0.18 s
embed-v-4-0Takes text, vision. Output modality not published.128K—$0.12$0.12/M——
command-a-plus-05-2026Takes text, vision, returns text.128K64K$2.5$10/M——
cohere-rerank-v4.0-fastTakes text. Output modality not published.33K—$0.068$0.068/M——
cohere-rerank-v4.0-proTakes text. Output modality not published.33K—$0.068$0.068/M——
cohere-rerank-v5-fastTakes text. Output modality not published.——$0.02$0.02/M——
cohere-rerank-v5-proTakes text. Output modality not published.——$0.05$0.05/M——
aihubmix-command-r-08-2024Takes text, returns text.——$0.2$0.8/M——
command-r-08-2024Takes text, returns text.——$0.2$0.8/M——
aihubmix-Cohere-command-rTakes text, returns text.——$0.64$1.92/M——
command-rTakes text, returns text.——$0.64$1.92/M——
commandTakes text, returns text.——$1$2/M——
command-lightTakes , returns text.——$1$2/M——
command-light-nightlyTakes , returns text.——$1$2/M——
command-nightlyTakes , returns text.——$1$2/M——
aihubmix-command-r-plus-08-2024Takes text, returns text.——$2.8$11.2/M——
command-r-plus-08-2024Takes text, returns text.——$2.8$11.2/M——
aihubmix-command-r-plusTakes text, returns text.——$3.84$19.2/M——
command-r-plusTakes text, returns text.——$3.84$19.2/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.

Cohere on AIHubMix

Which Cohere model should I start with?

north-mini-code-free is free on input — the cheapest entry here that declares tool calling, and it carries a 256K context. Move up to aihubmix-command-r-plus when answer quality matters more than cost, or to command-a-plus-05-2026 for long-form reasoning.

Which of these models reason before answering?

2 of the 21 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.

Do I need a separate Cohere 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 Cohere in one line

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