ChatCompletionRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "ChatCompletionRequest",
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "The model identifier, e.g. @cf/meta/llama-3.1-8b-instruct."
    },
    "messages": {
      "type": "array"
    },
    "max_tokens": {
      "type": "integer",
      "description": "Maximum number of tokens to generate."
    },
    "temperature": {
      "type": "number",
      "description": "Sampling temperature between 0 and 2."
    },
    "top_p": {
      "type": "number",
      "description": "Nucleus sampling parameter."
    },
    "stream": {
      "type": "boolean",
      "description": "Whether to stream the response via server-sent events."
    }
  }
}