Using Chat API

Scaleway Generative APIs are designed as a drop-in replacement for the OpenAI APIs. If you have an LLM-driven application that uses one of OpenAI’s client libraries, you can easily configure it to point to Scaleway Chat API, and get your existing applications running using open-weight instruct models hosted at Scaleway.

Create chat completion

Creates a model response for the given chat conversation.

Request sample:

curl --request POST \
     --url https://api.scaleway.ai/v1/chat/completions \
     --header 'Authorization: Bearer ${SCW_SECRET_KEY}' \
     --header 'Content-Type: application/json' \
     --data '{
     "model": "llama-3.1-8b-instruct",
     "messages": [
      {
        "role": "system",
        "content": "<string>"
      },
      {
        "role": "user",
        "content": "<string>"
      }
     ],
     "max_tokens": integer,
     "temperature": float,
     "top_p": float,
     "presence_penalty": float,
     "stop": "<string>",
     "stream": boolean,
     }'

Headers

Find required headers in this page.

Body

Required parameters

Our chat API is OpenAI compatible. Use OpenAI’s API reference for more detailed information on the usage.

Supported parameters

• temperature
• top_p
• max_tokens
• stream
• stream_options
• presence_penalty
• response_format
• logprobs
• stop
• seed
• tools
• tool_choice

Unsupported parameters

• frequency_penalty
• n
• top_logprobs
• logit_bias
• user

If you have a use case requiring one of these unsupported parameters, please contact us via Slack on #ai channel.

Going further

1. Python code examples to query text models using Scaleway’s Chat API
2. How to use structured outputs with the response_format parameter
3. How to use function calling with tools and tool_choice