GLM 5.3

{
  "id": "ec57729c-75ab-4d58-bb16-24305e482df7",
  "model": "glm-5.3",
  "usage": {
    "total_tokens": 263,
    "prompt_tokens": 13,
    "completion_tokens": 250,
    "prompt_tokens_details": {
      "cached_tokens": 0
    },
    "completion_tokens_details": {
      "reasoning_tokens": 213
    }
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm your GLM model trained by Z.ai. How can I help you today? Feel free to ask any questions or share topics you'd like to discuss.",
        "reasoning_content": "Let me consider how to respond to this greeting effectively.\n\nThe user has initiated contact with a simple \"hello,\" which suggests they may be testing the waters or just starting the conversation. This calls for a warm and inviting response that encourages further interaction.\n\nI should acknowledge their greeting in a friendly way and make them feel welcome to share more about what they need help with. It would be good to keep the tone approachable and professional, while also being open to various types of questions they might have.\n\nSince they haven't specified any particular topic or question, I should keep my response flexible and inviting. Perhaps I could offer some guidance on what I can assist with, while leaving the door open for them to direct the conversation.\n\nThe response should be concise yet welcoming, making it easy for them to continue the dialogue if they wish. I want to strike a balance between being helpful and not overwhelming them with too much information.\n\nLet me craft a response that is warm, professional, and open-ended - something that makes them feel comfortable sharing more about what they're looking for."
      },
      "finish_reason": "stop"
    }
  ],
  "created": 1787113497,
  "openmodels_cost": 9944
}

{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "model",
    "messages"
  ],
  "properties": {
    "n": {
      "type": "integer",
      "default": 1,
      "maximum": 128,
      "minimum": 1,
      "description": "Number of choices to generate"
    },
    "seed": {
      "type": "integer",
      "description": "Seed for deterministic sampling"
    },
    "stop": {
      "type": [
        "string",
        "array"
      ],
      "items": {
        "type": "string"
      },
      "description": "Sequences that stop generation"
    },
    "model": {
      "type": "string",
      "description": "The model to use"
    },
    "route": {
      "type": "object",
      "description": "OpenAny route configuration, including provider and other routing parameters"
    },
    "tools": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "Tools available to the model"
    },
    "top_p": {
      "type": "number",
      "default": 1,
      "maximum": 1,
      "minimum": 0,
      "description": "Nucleus sampling probability"
    },
    "stream": {
      "type": "boolean",
      "default": false,
      "description": "Whether to stream the response"
    },
    "user_id": {
      "type": "string",
      "description": "End-user identifier associated with the request."
    },
    "messages": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "The conversation messages"
    },
    "thinking": {
      "type": "object",
      "description": "Thinking configuration object for GLM reasoning behavior. eg: {\"type\": \"disabled\" }"
    },
    "do_sample": {
      "type": "boolean",
      "default": true,
      "description": "Whether to enable sampling. When true, the model uses sampling-based generation."
    },
    "max_tokens": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum completion tokens"
    },
    "request_id": {
      "type": "string",
      "description": "Client-provided request identifier for tracing and idempotency."
    },
    "route_mode": {
      "type": "string",
      "description": "The mode for routing the request"
    },
    "temperature": {
      "type": "number",
      "default": 1,
      "maximum": 2,
      "minimum": 0,
      "description": "Sampling temperature"
    },
    "tool_choice": {
      "enum": [
        "none",
        "auto",
        "required"
      ],
      "type": [
        "string",
        "object"
      ],
      "description": "Tool selection policy: string modes none, auto, or required, or an object selecting a specific tool"
    },
    "tool_stream": {
      "type": "boolean",
      "default": false,
      "description": "Whether to enable streaming output for tool calls."
    },
    "response_format": {
      "type": "object",
      "description": "Format constraint for the response"
    },
    "presence_penalty": {
      "type": "number",
      "default": 0,
      "maximum": 2,
      "minimum": -2,
      "description": "Penalty for previously used tokens"
    },
    "reasoning_effort": {
      "enum": [
        "max",
        "xhigh",
        "high",
        "medium",
        "low",
        "minimal",
        "none"
      ],
      "type": "string",
      "description": "Controls the reasoning effort level used by the model."
    },
    "frequency_penalty": {
      "type": "number",
      "default": 0,
      "maximum": 2,
      "minimum": -2,
      "description": "Penalty for repeated tokens"
    },
    "max_completion_tokens": {
      "type": "integer",
      "minimum": 1,
      "description": "Maximum visible completion tokens"
    }
  }
}