Baseten · Schema

MessagesRequest

Request body for creating a message.

AIMLInferenceDeploymentMLOpsOpenAI CompatibleAnthropic CompatibleTruss

Properties

Name	Type	Description
model	string	The model slug to use. Find available models at [Model APIs](https://app.baseten.co/model-apis/create).
messages	array	The conversation history as an ordered list of input messages. Alternating `user` and `assistant` roles are expected; the final message must be from the `user`.
max_tokens	integer	The maximum number of tokens to generate in the response. Required by the Messages API. The response may be shorter if it finishes naturally or hits a stop sequence.
system	object	A system prompt that sets the model's behavior. Pass either a single string or an array of text content blocks.
temperature	number	Controls randomness. Lower values are more deterministic. Range: 0 to 1.
top_p	number	Nucleus sampling: only consider tokens with cumulative probability up to this value.
top_k	integer	Limits token selection to the top K most probable tokens at each step.
stop_sequences	array	Custom text sequences that will stop generation. When a stop sequence is hit, `stop_reason` is `stop_sequence` and `stop_sequence` contains the matched string.
stream	boolean	If `true`, the response is streamed as server-sent events. Each event has a `type` such as `message_start`, `content_block_delta`, or `message_stop`.
tools	array	A list of tools the model may call. Each tool has a `name`, `description`, and `input_schema` (a JSON Schema object).
tool_choice	object	Controls which tool (if any) the model must call.
metadata	object	An object describing metadata about the request. Supports `user_id` for abuse detection.

View JSON Schema on GitHub

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/MessagesRequest",
  "title": "MessagesRequest",
  "additionalProperties": false,
  "type": "object",
  "required": [
    "model",
    "messages",
    "max_tokens"
  ],
  "description": "Request body for creating a message.",
  "properties": {
    "model": {
      "type": "string",
      "title": "Model",
      "description": "The model slug to use. Find available models at [Model APIs](https://app.baseten.co/model-apis/create)."
    },
    "messages": {
      "type": "array",
      "title": "Messages",
      "description": "The conversation history as an ordered list of input messages. Alternating `user` and `assistant` roles are expected; the final message must be from the `user`.",
      "items": {
        "$ref": "#/components/schemas/InputMessage"
      }
    },
    "max_tokens": {
      "type": "integer",
      "minimum": 1,
      "title": "Max Tokens",
      "description": "The maximum number of tokens to generate in the response. Required by the Messages API. The response may be shorter if it finishes naturally or hits a stop sequence."
    },
    "system": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/TextBlock"
          }
        }
      ],
      "title": "System",
      "description": "A system prompt that sets the model's behavior. Pass either a single string or an array of text content blocks."
    },
    "temperature": {
      "type": "number",
      "minimum": 0,
      "maximum": 1,
      "default": 1,
      "title": "Temperature",
      "description": "Controls randomness. Lower values are more deterministic. Range: 0 to 1."
    },
    "top_p": {
      "type": "number",
      "exclusiveMinimum": 0,
      "maximum": 1,
      "title": "Top P",
      "description": "Nucleus sampling: only consider tokens with cumulative probability up to this value."
    },
    "top_k": {
      "type": "integer",
      "minimum": 0,
      "title": "Top K",
      "description": "Limits token selection to the top K most probable tokens at each step."
    },
    "stop_sequences": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "title": "Stop Sequences",
      "description": "Custom text sequences that will stop generation. When a stop sequence is hit, `stop_reason` is `stop_sequence` and `stop_sequence` contains the matched string."
    },
    "stream": {
      "type": "boolean",
      "default": false,
      "title": "Stream",
      "description": "If `true`, the response is streamed as server-sent events. Each event has a `type` such as `message_start`, `content_block_delta`, or `message_stop`."
    },
    "tools": {
      "type": "array",
      "items": {
        "$ref": "#/components/schemas/ToolDefinition"
      },
      "title": "Tools",
      "description": "A list of tools the model may call. Each tool has a `name`, `description`, and `input_schema` (a JSON Schema object)."
    },
    "tool_choice": {
      "$ref": "#/components/schemas/ToolChoice",
      "description": "Controls which tool (if any) the model must call."
    },
    "metadata": {
      "type": "object",
      "title": "Metadata",
      "description": "An object describing metadata about the request. Supports `user_id` for abuse detection.",
      "properties": {
        "user_id": {
          "type": "string",
          "description": "An external identifier for the end user."
        }
      }
    }
  }
}