Text Generation

Using the Cohere Chat API for Text Generation

The Chat API endpoint is used to generate text with Cohere LLMs. This endpoint facilitates a conversational interface, allowing users to send messages to the model and receive text responses.

import cohere
co = cohere.Client(api_key="<YOUR API KEY>")
response = co.chat(
    model="command-a-03-2025",
    message="Write a title for a blog post about API design. Only output the title text.",
)
print(response.text)
# "The Art of API Design: Crafting Elegant and Powerful Interfaces"

Response Structure

Below is a sample response from the Chat API

JSON
{
    "text": "The Art of API Design: Crafting Elegant and Powerful Interfaces",
    "generation_id": "dd78b9fe-988b-4c18-9419-8fbdf9968948",
    "chat_history": [
        {
            "role": "USER",
            "message": "Write a title for a blog post about API design. Only output the title text."
        },
        {
            "role": "CHATBOT",
            "message": "The Art of API Design: Crafting Elegant and Powerful Interfaces"
        }
    ],
    "finish_reason": "COMPLETE",
    "meta": {
        "api_version": {
            "version": "1"
        },
        "billed_units": {
            "input_tokens": 17,
            "output_tokens": 12
        },
        "tokens": {
            "input_tokens": 83,
            "output_tokens": 12
        }
    }
}

Every response contains the following fields:

  • text the generated message from the model.
  • generation_id the ID corresponding to this response. Can be used together with the Feedback API endpoint to promote great responses and flag bad ones.
  • chat_history the conversation presented in a chat log format
  • finish_reason can be one of the following:
    • COMPLETE the model successfully finished generating the message
    • MAX_TOKENS the model’s context limit was reached before the generation could be completed
  • meta contains information with token counts, billing etc.

Multi-turn conversations

The user message in the Chat request can be sent together with a chat_history to provide the model with conversational context:

PYTHON
import cohere
co = cohere.Client(api_key="<YOUR API KEY>")
message = "Can you tell me about LLMs?"
response = co.chat(
    model="command-a-03-2025",
    chat_history=[
        {"role": "USER", "text": "Hey, my name is Michael!"},
        {
            "role": "CHATBOT",
            "text": "Hey Michael! How can I help you today?",
        },
    ],
    message=message,
)
print(response.text)  # "Sure thing Michael, LLMs are ..."

Instead of manually building the chat_history, we can grab it from the response of the previous turn.

PYTHON
chat_history = []
max_turns = 10
for _ in range(max_turns):
    # get user input
    message = input("Send the model a message: ")
    # generate a response with the current chat history
    response = co.chat(
        model="command-a-03-2025",
        message=message,
        chat_history=chat_history,
    )
    # print the model's response on this turn
    print(response.text)
    # set the chat history for next turn
    chat_history = response.chat_history

Using conversation_id to Save Chat History

Providing the model with the conversation history is one way to have a multi-turn conversation with the model. Cohere has developed another option for users who do not wish to save the conversation history, and it works through a user-defined conversation_id.

PYTHON
import cohere
co = cohere.Client("<YOUR API KEY>")
response = co.chat(
    model="command-a-03-2025",
    message="The secret word is 'fish', remember that.",
    conversation_id="user_defined_id_1",
)
answer = response.text

Then, if you wanted to continue the conversation, you could do so like this (keeping the id consistent):

PYTHON
response2 = co.chat(
    model="command-a-03-2025",
    message="What is the secret word?",
    conversation_id="user_defined_id_1",
)
print(response2.text)  # "The secret word is 'fish'"

Note that the conversation_id should not be used in conjunction with the chat_history. They are mutually exclusive.