The Cohere platform builds natural language processing and generation into your product with a few lines of code. Our large language models can solve a broad spectrum of natural language use cases, including classification, semantic search, paraphrasing, summarization, and content generation.

By training a custom model, users can customize large language models to their use case and trained on their data.

The models can be accessed through the playground, SDK, and the CLI tool.


We support SDKs in 4 different languages. Please see the following installation methods and snippets to get started.


python -m pip install cohere --upgrade
import cohere

co = cohere.Client("<<apiKey>>")

response =
	message="hello world!"



npm i -s cohere-ai
const { CohereClient } = require('cohere-ai');

const cohere = new CohereClient({
  token: '<<apiKey>>',

(async () => {
  const response = await{
		message: "hello world!"



implementation 'com.cohere:cohere-java:1.x.x'
import com.cohere.api.Cohere;
import com.cohere.api.requests.ChatRequest;
import com.cohere.api.types.ChatMessage;
import com.cohere.api.types.ChatMessageRole;
import com.cohere.api.types.NonStreamedChatResponse;

import java.util.List;

public class ChatPost {
    public static void main(String[] args) {
        Cohere cohere = Cohere.builder().token("<<apiKey>>").build();

        NonStreamedChatResponse response =
                        .message("What year was he born?").build());



go get
package main

import (

	cohere ""
	client ""

func main() {
	co := client.NewClient(client.WithToken("<<apiKey>>"))

	resp, err := co.Chat(
			Message: "Hello world!",

	if err != nil {

	log.Printf("%+v", resp)

Request Specification

To make a request to any model, you must pass in the Authorization Header and the request must be made through a POST request.

The content of Authorization should be in the shape of BEARER [API_KEY]. All request bodies are sent through JSON.

Model names are found within the dashboard, and details about endpoints are available within the documentation.

Detailed model information can be found in the Model Cards.