cohere

cohere Permissive license MIT Active ★ 396 v7.0.8 released 2026-07-23

Install

cohere on PyPI

pip

pip install cohere

uv

uv add cohere

poetry

poetry add cohere

Package facts

License	MIT (permissive)
Python support	supports the current Python release (<4.0,>=3.10)
Install friction	low — pure-Python wheel
Runtime dependencies	8 — fastavro, httpx, pydantic, pydantic-core, requests, tokenizers, types-requests, typing_extensions
Maintenance	actively maintained — 21 days since the last release
Last repo commit	2026-07-23
First released	2021-01-20
Popularity	one of the top 1,000 most-downloaded packages on PyPI (30-day window, as of 2026-08-13)
Known vulnerabilities	none known (OSV.dev, checked 2026-08-13)

Evidence: cohere-7.0.8-py3-none-any.whl

Intended Audience :: DevelopersLicense :: OSI Approved :: MIT LicenseOperating System :: MacOSOperating System :: Microsoft :: WindowsOperating System :: OS IndependentOperating System :: POSIXOperating System :: POSIX :: LinuxProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.13Programming Language :: Python :: 3.14Programming Language :: Python :: 3.15Topic :: Software Development :: Libraries :: Python ModulesTyping :: Typed

About cohere

from the package's own PyPI description — quoted content, verbatim

Cohere Python SDK

banner.png (image)

version badge (image) license badge (image) fern shield (image)

The Cohere Python SDK allows access to Cohere models across many different platforms: the cohere platform, AWS (Bedrock, Sagemaker), Azure, GCP and Oracle OCI. For a full list of support and snippets, please take a look at the SDK support docs page.

Documentation

Cohere documentation and API reference is available here.

Installation

pip install cohere

Usage

import cohere

co = cohere.ClientV2()

response = co.chat(
    model="command-r-plus-08-2024",
    messages=[{"role": "user", "content": "hello world!"}],
)

print(response)

> [!TIP] > You can set a system environment variable CO_API_KEY to avoid writing your api key within your code, e.g. add export CO_API_KEY=theapikeyforyouraccount > in your ~/.zshrc or...

Read as markdown · JSON record · Source repository

AI interpretation — verify before relying

AI-generated interpretation of the package facts above; every digit, version, license, or vulnerability id it cites is grounded in the facts already shown on this page

The Cohere Python SDK provides programmatic access to Cohere's large language models for chat, embedding, and text generation across multiple cloud platforms including AWS, Azure, GCP, and Oracle OCI.

Low friction install with a pure-Python wheel and eight well-maintained runtime dependencies. Active maintenance with a release 21 days ago and recent repository activity.

MIT license permits commercial and private use with minimal restrictions; you may use, modify, and distribute this package freely provided you retain the license notice.

Usage

pip install cohere

import cohere

co = cohere.ClientV2()
response = co.chat(
    model="command-r-plus-08-2024",
    messages=[{"role": "user", "content": "hello world!"}],
)
print(response)

Requires Python 3.10 or later; API key must be provided via CO_API_KEY environment variable or passed to the client.

Verdict: A well-maintained, actively developed SDK for accessing Cohere's generative AI models with low installation friction and permissive MIT licensing. No known security vulnerabilities and broad Python version support (3.10–3.15) make it production-ready for multi-cloud AI integrations.

Needs verification

Whether the eight runtime dependencies (fastavro, httpx, pydantic, pydantic-core, requests, tokenizers, types-requests, typing_extensions) introduce any transitive security or maintenance concerns beyond what OSV reports.
Whether the OCI optional extra (`cohere[oci]`) introduces additional dependencies or licensing implications not reflected in the base fact sheet.

cohere api clientllm chat sdk pythontext embedding servicegenerative ai platform sdkmulti-cloud ai modelscohere language model accessstreaming chat completion