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 completionLink to this anchor

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,
     }'

HeadersLink to this anchor

Find required headers in

BodyLink to this anchor

Required parametersLink to this anchor

Our chat API is OpenAI compatible. Use OpenAI’s

Supported parametersLink to this anchor

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

Unsupported parametersLink to this anchor

• frequency_penalty
• n
• top_logprobs
• logit_bias
• user

If you have a use case requiring one of these unsupported parameters, please

Going furtherLink to this anchor

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