Claude Sonnet 4.6

{
  "id": "msg_bdrk_01Bg1KUdHeA2Nf2TMgxsQ2P2",
  "model": "claude-sonnet-4-6",
  "usage": {
    "input_tokens": 0,
    "total_tokens": 31,
    "output_tokens": 0,
    "prompt_tokens": 8,
    "completion_tokens": 23,
    "input_tokens_details": null,
    "prompt_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "text_tokens": 0,
      "audio_tokens": 0,
      "image_tokens": 0,
      "reasoning_tokens": 0
    },
    "claude_cache_creation_1_h_tokens": 0,
    "claude_cache_creation_5_m_tokens": 0
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How are you doing? Is there something I can help you with today? 😊"
      },
      "finish_reason": "stop"
    }
  ],
  "created": 1784810011,
  "openmodels_cost": 380
}

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "max_tokens",
    "messages",
    "model"
  ],
  "properties": {
    "model": {
      "type": "string"
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Tools available to the model. Each tool should define name, description, and input_schema."
    },
    "top_k": {
      "type": "integer",
      "description": "Sample only from the top K most likely tokens. Prefer changing only one of temperature, top_p, or top_k."
    },
    "top_p": {
      "type": "number",
      "maximum": 1,
      "minimum": 0,
      "description": "Nucleus sampling threshold from 0.0 to 1.0. Prefer changing only one of temperature, top_p, or top_k."
    },
    "stream": {
      "type": "boolean",
      "default": false,
      "description": "Whether to enable Server-Sent Events streaming output."
    },
    "system": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "array",
          "items": {
            "type": "object",
            "required": [
              "type",
              "text"
            ],
            "properties": {
              "text": {
                "type": "string"
              },
              "type": {
                "const": "text"
              }
            }
          }
        }
      ]
    },
    "messages": {
      "type": "array",
      "items": {
        "type": "object",
        "required": [
          "role",
          "content"
        ],
        "properties": {
          "role": {
            "enum": [
              "user",
              "assistant"
            ],
            "type": "string",
            "description": "Message role. The Messages API does not support a system role inside messages; use the top-level system parameter instead."
          },
          "content": {
            "anyOf": [
              {
                "type": "string"
              },
              {
                "type": "array",
                "items": {
                  "type": "object",
                  "required": [
                    "type"
                  ],
                  "properties": {
                    "type": {
                      "type": "string"
                    }
                  }
                }
              }
            ],
            "description": "Message content. Can be a string or an array of typed content blocks such as text, image, tool_result, or document blocks."
          }
        }
      }
    },
    "metadata": {
      "type": "object",
      "properties": {
        "user_id": {
          "type": "string",
          "description": "End-user identifier used for abuse monitoring and tracing."
        }
      },
      "description": "Metadata object. Can include user_id to identify the end user for abuse monitoring and tracing. Example: {\"user_id\":\"user-123\"}."
    },
    "thinking": {
      "type": "object",
      "properties": {
        "type": {
          "enum": [
            "adaptive",
            "enabled"
          ],
          "type": "string",
          "description": "Thinking mode type. adaptive is recommended and lets the model decide when and how deeply to think. enabled is supported by older models and usually requires budget_tokens."
        },
        "budget_tokens": {
          "type": "integer",
          "description": "Token budget for extended thinking. Used with older enabled thinking mode when supported by the model."
        }
      },
      "description": "Extended thinking configuration for supported models."
    },
    "max_tokens": {
      "type": "integer",
      "description": "Maximum number of tokens to generate. This is required by Anthropic and is a hard limit for total output, including thinking and visible response content."
    },
    "temperature": {
      "type": "number",
      "default": 1,
      "maximum": 1,
      "minimum": 0,
      "description": "Sampling temperature from 0.0 to 1.0. Higher values make output more random; lower values make output more deterministic. Prefer changing only one of temperature, top_p, or top_k."
    },
    "tool_choice": {
      "type": "object",
      "default": {
        "type": "auto"
      },
      "description": "Controls tool use behavior. Use {\"type\":\"auto\"}, {\"type\":\"any\"}, or {\"type\":\"tool\",\"name\":\"tool_name\"}."
    },
    "stop_sequences": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Custom stop sequences. Supports up to 4 strings. Generation stops when any sequence is produced, and the stop sequence is not included in the output."
    }
  }
}