Skip to main content
You are currently on a page documenting the use of Cohere models as text completion models. Many popular Cohere models are chat completion models.You may be looking for this page instead.
Cohere is a Canadian startup that provides natural language processing models that help companies improve human-machine interactions.
Head to the API reference for detailed documentation of all attributes and methods.

​
Overview

​
Integration details

ClassPackageLocalSerializableJS supportDownloadsVersion
Coherelangchain-community❌beta✅PyPI - DownloadsPyPI - Version

​
Setup

The integration lives in the langchain-community package. We also need to install the cohere package itself. We can install these with:

​
Credentials

We’ll need to get a Cohere API key and set the COHERE_API_KEY environment variable: 
import getpass
import os

if "COHERE_API_KEY" not in os.environ:
    os.environ["COHERE_API_KEY"] = getpass.getpass()

​
Installation

pip install -U langchain-community langchain-cohere
It’s also helpful (but not needed) to set up LangSmith for best-in-class observability 
os.environ["LANGSMITH_TRACING"] = "true"
# os.environ["LANGSMITH_API_KEY"] = getpass.getpass()

​
Invocation

Cohere supports all LLM functionality: 
from langchain_cohere import Cohere
from langchain.messages import HumanMessage

model = Cohere(max_tokens=256, temperature=0.75)

message = "Knock knock"
model.invoke(message)

" Who's there?"

await model.ainvoke(message)

" Who's there?"

for chunk in model.stream(message):
    print(chunk, end="", flush=True)

 Who's there?

model.batch([message])

[" Who's there?"]

​
API reference

For detailed documentation of all Cohere llm features and configurations head to the API reference: python.langchain.com/api_reference/community/llms/langchain_community.llms.cohere.Cohere.html
Edit the source of this page on GitHub.
Connect these docs programmatically to Claude, VSCode, and more via MCP for real-time answers.
⌘I