CompleteRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "CompleteRequest",
  "type": "object",
  "description": "LLM text completion request.",
  "properties": {
    "model": {
      "type": "string",
      "description": "The model name. See documentation for possible values."
    },
    "messages": {
      "type": "array"
    },
    "temperature": {
      "type": "number",
      "description": "Temperature controls the amount of randomness used in response generation. A higher temperature corresponds to more randomness."
    },
    "top_p": {
      "type": "number",
      "description": "Threshold probability for nucleus sampling. A higher top-p value increases the diversity of tokens that the model considers, while a lower value results in more predictable output."
    },
    "max_tokens": {
      "type": "integer",
      "description": "The maximum number of output tokens to produce. The default value is model-dependent."
    },
    "max_output_tokens": {
      "type": "integer",
      "description": "Deprecated in favor of \"max_tokens\", which has identical behavior."
    },
    "response_format": {
      "type": "object",
      "description": "An object describing response format config for structured-output mode."
    },
    "tools": {
      "type": "array",
      "description": "List of tools to be used during tool calling"
    },
    "provisioned_throughput_id": {
      "type": "string",
      "description": "The provisioned throughput ID to be used with the request."
    },
    "sf-ml-xp-inflight-prompt-action": {
      "type": "string",
      "description": "Reserved"
    },
    "sf-ml-xp-inflight-prompt-client-id": {
      "type": "string",
      "description": "Reserved"
    },
    "sf-ml-xp-inflight-prompt-public-key": {
      "type": "string",
      "description": "Reserved"
    },
    "stream": {
      "type": "boolean",
      "description": "Reserved"
    }
  }
}