CreateMessageRequest

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "#/components/schemas/CreateMessageRequest",
  "title": "CreateMessageRequest",
  "type": "object",
  "required": [
    "model",
    "max_tokens",
    "messages"
  ],
  "properties": {
    "model": {
      "type": "string",
      "description": "The model that will complete your prompt. See the list of available models.",
      "example": "claude-sonnet-4-6"
    },
    "max_tokens": {
      "type": "integer",
      "description": "The maximum number of tokens to generate before stopping. Different models support different maximum values.",
      "minimum": 1,
      "example": 1024
    },
    "messages": {
      "type": "array",
      "description": "Input messages. Alternating user and assistant conversational turns. Maximum 100,000 messages per request.",
      "items": {
        "$ref": "#/components/schemas/MessageParam"
      },
      "minItems": 1,
      "example": []
    },
    "system": {
      "description": "System prompt providing context and instructions to Claude. Can be a string or array of content blocks.",
      "oneOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "$ref": "#/components/schemas/TextBlockParam"
          }
        }
      ],
      "example": "example_value"
    },
    "temperature": {
      "type": "number",
      "description": "Amount of randomness injected into the response. Ranges from 0.0 to 1.0. Use closer to 0.0 for analytical tasks, closer to 1.0 for creative tasks.",
      "minimum": 0.0,
      "maximum": 1.0,
      "default": 1.0,
      "example": 42.5
    },
    "top_p": {
      "type": "number",
      "description": "Use nucleus sampling. Recommended to use either temperature or top_p, but not both.",
      "minimum": 0.0,
      "maximum": 1.0,
      "example": 42.5
    },
    "top_k": {
      "type": "integer",
      "description": "Only sample from the top K options for each subsequent token.",
      "minimum": 1,
      "example": 10
    },
    "stop_sequences": {
      "type": "array",
      "description": "Custom text sequences that will cause the model to stop generating.",
      "items": {
        "type": "string"
      },
      "example": []
    },
    "stream": {
      "type": "boolean",
      "description": "Whether to incrementally stream the response using server-sent events.",
      "default": false,
      "example": true
    },
    "metadata": {
      "$ref": "#/components/schemas/Metadata"
    },
    "tools": {
      "type": "array",
      "description": "Definitions of tools that the model may use.",
      "items": {
        "$ref": "#/components/schemas/Tool"
      },
      "example": []
    },
    "tool_choice": {
      "$ref": "#/components/schemas/ToolChoice"
    },
    "thinking": {
      "$ref": "#/components/schemas/ThinkingConfig"
    },
    "output_config": {
      "$ref": "#/components/schemas/OutputConfig"
    },
    "service_tier": {
      "type": "string",
      "description": "Service tier to use for this request.",
      "enum": [
        "auto",
        "standard_only"
      ],
      "default": "auto",
      "example": "auto"
    },
    "cache_control": {
      "$ref": "#/components/schemas/CacheControl"
    }
  }
}