AIHubMixAIHubMix

Cohere Models

19 modelsGeneral models free to startUp to 256K context

Usage

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

Tokens

632M

Requests

577K

Models in use

19 of 19

Tokens per day

0263M525M07-1307-2007-2708-0308-102026-07-13 — 525,458,910 tokens2026-07-14 — 11,315 tokens2026-07-15 — 2,289,740 tokens2026-07-16 — 26,615 tokens2026-07-17 — 16,230 tokens2026-07-18 — 3,240 tokens2026-07-19 — 788,465 tokens2026-07-20 — 309,815 tokens2026-07-21 — 136,615 tokens2026-07-22 — 8,400 tokens2026-07-23 — 14,980 tokens2026-07-24 — 27,579,200 tokens2026-07-25 — 9,510 tokens2026-07-26 — 231,525 tokens2026-07-27 — 196,340 tokens2026-07-28 — 2,430,545 tokens2026-07-29 — 7,180,545 tokens2026-07-30 — 4,984,405 tokens2026-07-31 — 7,106,385 tokens2026-08-01 — 7,248,025 tokens2026-08-02 — 10,166,510 tokens2026-08-03 — 11,951,915 tokens2026-08-04 — 203,675 tokens2026-08-05 — 837,785 tokens2026-08-06 — 15,114,305 tokens2026-08-07 — 1,406,720 tokens2026-08-08 — 3,977,225 tokens2026-08-09 — 2,353,265 tokens2026-08-10 — 16,430 tokens2026-08-11 — 3,175 tokens

Which models that traffic went to

  1. embed-v-4-099.0%626M
  2. north-mini-code-free0.5%3.3M
  3. command-a-plus-05-20260.3%2M
  4. command-a-03-20250.1%351K
  5. cohere-command-a<0.1%268K
  6. command-nightly<0.1%22.9K

Share of 632M tokens. 13 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 19 model IDs listed on this page; traffic routed through upstream-specific IDs that are not in the public catalog is not included.

All 19 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.256K—FreeFree/M——
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$2.50$10.00/M55 tok/s0.93 s
cohere-rerank-v4.0-fastTakes text, vision. Output modality not published.——$0.07$0.07/M——
cohere-rerank-v4.0-proTakes text, vision. Output modality not published.——$0.07$0.07/M——
aihubmix-command-r-08-2024Takes text, returns text.——$0.20$0.80/M——
command-r-08-2024Takes text, returns text.——$0.20$0.80/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.——$1.00$2.00/M——
command-light——$1.00$2.00/M——
command-light-nightly——$1.00$2.00/M——
command-nightly——$1.00$2.00/M——
cohere-command-aTakes text, returns text.——$2.50$10.00/M——
command-a-03-2025Takes text, returns text.——$2.50$10.00/M——
aihubmix-command-r-plus-08-2024Takes text, returns text.——$2.80$11.20/M——
command-r-plus-08-2024Takes text, returns text.——$2.80$11.20/M——
aihubmix-command-r-plusTakes text, returns text.——$3.84$19.20/M——
command-r-plusTakes text, returns text.——$3.84$19.20/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

aihubmix-Cohere-command-r vs aihubmix-command-r-08-2024aihubmix-Cohere-command-r vs aihubmix-command-r-plusaihubmix-Cohere-command-r vs aihubmix-command-r-plus-08-2024aihubmix-Cohere-command-r vs qwen3.8-max-previewaihubmix-Cohere-command-r vs kimi-k3

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 19 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.

Other Providers

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

Start calling Cohere 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