Skip to content
Llama API Docs
  • Auto
  • Light
  • Dark
Log in to API

Chat completion with Llama API

Chat completion lets developers create text based on a given prompt or conversation history. This feature uses a Llama model to predict the next word or sequence of words in a conversation, allowing developers to create AI models that can respond to user input in a natural and intuitive way.

How it works

Section titled “How it works”

Chat completion enables models to process a sequence of messages with different roles and generate appropriate responses.

Llama API supports three distinct roles in conversations:

  • System messages: Define overall behavior instructions for the model.
  • User messages: Represent inputs from your application’s users.
  • Assistant messages: Contain previous responses from the model.

Structuring a conversation into these roles allows developers to provide the model with context across multiple interactions, ensuring coherent, contextually relevant responses.

Use cases

Section titled “Use cases”

Use chat completion to build sophisticated conversational experiences, such as:

  • Customer Support: Create intelligent assistants that can handle inquiries and resolve issues.
  • Content Creation: Generate ideas, outlines, and drafts through interactive dialogue.
  • Education: Build tutoring systems that adapt explanations based on student questions.
  • Information Retrieval: Develop question-answering systems that provide concise, relevant information.

Getting started: A simple example

Section titled “Getting started: A simple example”

You can create a basic conversation with Llama API using a standard HTTP request.

Here’s how to implement a simple chat using cURL:

curl
curl "https://api.llama.com/v1/chat/completions" \
  -H "Authorization: Bearer $LLAMA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "Llama-4-Maverick-17B-128E-Instruct-FP8",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant that provides concise answers."
      },
      {
        "role": "user",
        "content": "What is the capital of France?"
      }
    ],
    "max_tokens": 256
  }'

Next steps

Section titled “Next steps”

Explore the full capabilities of Llama API with these resources: