Jahanzaib

Cohere models

Cohere has 24 models in the directory. The newest is Embed 5 Fast, released Sep 30, 2026.

The cheapest to run is Command R7B Arabic at $0.0375 per million input tokens.

North Mini Code (free) has the longest context window, 256K tokens.

Command A+ scores highest on the independent Intelligence Index, at 13.1.

Models
24
Newest
Sep 30, 2026
From
$0.0375/M input
Longest context
256K

All Cohere models

Filter in the directory

  • Embed 5 Fast

    Embeddings

    Turns text into vectors for search and retrieval.

    by cohereSep 30, 2026

  • Embed 5 Pro

    Embeddings

    Turns text into vectors for search and retrieval.

    by cohereSep 30, 2026

  • North Small Translate

    Reads text.

    by cohereSep 9, 2026$0/M input tokens$0/M output tokens

  • North Mini Code (free)

    Reads text. Tool calling, reasoning.

    by cohereJun 17, 2026$0/M input tokens$0/M output tokens

  • North Mini Code

    Index 9.9

    Reads text. Tool calling, structured output, reasoning.

    by cohereJun 9, 2026256K context$0/M input tokens$0/M output tokens

  • Command A+

    Index 13.1

    Reads text and images. Tool calling, structured output, reasoning. Served by 2 providers.

    by cohereMay 20, 2026192K context$0.30/M input tokens$1.50/M output tokens2 providers

  • Tiny Aya Earth

    Reads text. Tool calling.

    by cohereFeb 17, 2026

  • Tiny Aya Fire

    Reads text. Tool calling.

    by cohereFeb 17, 2026

  • Tiny Aya Global

    Reads text. Tool calling.

    by cohereFeb 17, 2026

  • Tiny Aya Water

    Reads text. Tool calling.

    by cohereFeb 17, 2026

  • Cohere Rerank 4 Fast

    Rerank

    Reorders search results by relevance to a query.

    by cohereDec 11, 2025

  • Cohere Rerank 4 Pro

    Rerank

    Reorders search results by relevance to a query.

    by cohereDec 11, 2025

  • Command A Translate

    Reads text. Tool calling.

    by cohereAug 28, 2025$2.50/M input tokens$10/M output tokens

  • Command A Reasoning

    Reads text. Tool calling, reasoning. Served by 3 providers.

    by cohereAug 21, 2025$2.50/M input tokens$10/M output tokens3 providers

  • Command A Vision

    Reads text and images.

    by cohereJul 31, 2025$2.50/M input tokens$10/M output tokens

  • Embed v4.0

    Embeddings

    Turns text into vectors for search and retrieval.

    by cohereApr 15, 2025

  • Command A

    Index 7

    Reads text. Tool calling, structured output. Served by 6 providers.

    by cohereMar 13, 2025256K context$2.50/M input tokens$10/M output tokens6 providers

  • Aya Vision 32B

    Reads text and images.

    by cohereMar 4, 2025

  • Command R7B Arabic

    Reads text. Tool calling.

    by cohereFeb 27, 2025$0.0375/M input tokens$0.15/M output tokens

  • Command R7B

    Reads text. Tool calling, structured output. Served by 5 providers.

    by cohereDec 2, 2024$0.0375/M input tokens$0.15/M output tokens5 providers

  • Cohere Rerank 3.5

    Rerank

    Reorders search results by relevance to a query.

    by cohereDec 2, 2024

  • Aya Expanse 32B

    Reads text. Served by 2 providers.

    by cohereOct 24, 2024$0.50/M input tokens$1.50/M output tokens2 providers

  • Command R

    Reads text. Tool calling, structured output. Served by 5 providers.

    by cohereAug 30, 2024$0.15/M input tokens$0.60/M output tokens5 providers

  • Command R+

    Reads text. Tool calling, structured output. Served by 7 providers.

    by cohereAug 30, 2024$2.50/M input tokens$10/M output tokens7 providers

Prices and context from models.dev (MIT licensed), refreshed Oct 15, 2026.

Not sure which Cohere model fits?

I benchmark the candidates on your own tasks and ship on the one that wins on cost and accuracy.

Book Meeting