Cohere Models
Usage
705M
51.4K
17 of 21
- 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
- embed-v-4-0
- cohere-command-a
- cohere-rerank-v4.0-fast
- command-a-03-2025
- cohere-rerank-v5-fast
- north-mini-code-free
- cohere-rerank-v4.0-pro
- cohere-rerank-v5-pro
- 9 more models
Which models that traffic went to
- Cohere Rerank V5 Fast80.1%565M
- Cohere Command A7.6%53.8M
- North Mini Code (free)6.4%44.9M
- Cohere Rerank V5 Pro2.9%20.7M
- Embed V 4.02.3%15.9M
- Command A 03 20250.7%4.7M
- Command Nightly<0.1%74.4K
- Embed V 4.068.2%35.1K
- Cohere Command A9.4%4.8K
- Cohere Rerank V4.0 Fast8.4%4.3K
- Command A 03 20254.2%2.1K
- Cohere Rerank V5 Fast3.8%1.9K
- North Mini Code (free)2.6%1.4K
- Cohere Rerank V4.0 Pro1.2%636
- Cohere Rerank V5 Pro0.9%451
- 9 more models1.3%682
All 21 Cohere Models
Open in model list| Modalities | ||||||
|---|---|---|---|---|---|---|
| north-mini-code-free | Takes text, returns text. | 256K | 64K | FreeFree/M | — | — |
| cohere-command-a | Takes text, returns text. | 256K | 8K | $2.5$10/M | 1 tok/s | 1.52 s |
| command-a-03-2025 | Takes text, returns text. | 256K | 8K | $2.5$10/M | 41 tok/s | 0.18 s |
| embed-v-4-0 | Takes text, vision. Output modality not published. | 128K | — | $0.12$0.12/M | — | — |
| command-a-plus-05-2026 | Takes text, vision, returns text. | 128K | 64K | $2.5$10/M | — | — |
| cohere-rerank-v4.0-fast | Takes text. Output modality not published. | 33K | — | $0.068$0.068/M | — | — |
| cohere-rerank-v4.0-pro | Takes text. Output modality not published. | 33K | — | $0.068$0.068/M | — | — |
| cohere-rerank-v5-fast | Takes text. Output modality not published. | — | — | $0.02$0.02/M | — | — |
| cohere-rerank-v5-pro | Takes text. Output modality not published. | — | — | $0.05$0.05/M | — | — |
| aihubmix-command-r-08-2024 | Takes text, returns text. | — | — | $0.2$0.8/M | — | — |
| command-r-08-2024 | Takes text, returns text. | — | — | $0.2$0.8/M | — | — |
| aihubmix-Cohere-command-r | Takes text, returns text. | — | — | $0.64$1.92/M | — | — |
| command-r | Takes text, returns text. | — | — | $0.64$1.92/M | — | — |
| command | Takes text, returns text. | — | — | $1$2/M | — | — |
| command-light | Takes , returns text. | — | — | $1$2/M | — | — |
| command-light-nightly | Takes , returns text. | — | — | $1$2/M | — | — |
| command-nightly | Takes , returns text. | — | — | $1$2/M | — | — |
| aihubmix-command-r-plus-08-2024 | Takes text, returns text. | — | — | $2.8$11.2/M | — | — |
| command-r-plus-08-2024 | Takes text, returns text. | — | — | $2.8$11.2/M | — | — |
| aihubmix-command-r-plus | Takes text, returns text. | — | — | $3.84$19.2/M | — | — |
| command-r-plus | Takes text, returns text. | — | — | $3.84$19.2/M | — | — |
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, 985 models across 49 model authors.
