> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyfast.ai/llms.txt > Use this file to discover all available pages before exploring further. # glm-5.3 > Creates a GLM-5.3 response for the supplied conversation. GLM-5.3 always uses thinking; thinking.type can only be enabled, and reasoning_effort can only be low, high, or max. ## OpenAPI ````yaml api-reference/model-api/zhipu/openapi/glm-5.3/openapi.yaml POST /v1/chat/completions openapi: 3.1.0 info: title: GLM-5.3 description: >- Zhipu AI's GLM-5.3 flagship reasoning model through the AnyFast OpenAI-compatible API. version: 1.0.0 servers: - url: https://www.anyfast.ai security: - bearerAuth: [] paths: /v1/chat/completions: post: summary: Create a GLM-5.3 chat completion description: >- Creates a GLM-5.3 response for the supplied conversation. GLM-5.3 always uses thinking; thinking.type can only be enabled, and reasoning_effort can only be low, high, or max. operationId: createChatCompletionGlm53 requestBody: required: true content: application/json: schema: type: object required: - model - messages properties: model: type: string enum: - glm-5.3 description: Model ID. Must be glm-5.3. example: glm-5.3 messages: type: array minItems: 1 description: The complete conversation in chronological order. items: type: object required: - role - content properties: role: type: string enum: - system - user - assistant - tool description: The message author. content: type: string description: Text content of the message. name: type: string description: Optional participant or tool name. tool_call_id: type: string description: Tool call ID when role is tool. example: - role: system content: You are a senior software engineer. - role: user content: Design a reliable distributed job queue. thinking: type: object description: >- Thinking configuration. Thinking remains enabled when this field is omitted. GLM-5.3 does not accept disabled. properties: type: type: string enum: - enabled default: enabled description: Only enabled is supported. reasoning_effort: type: string enum: - low - high - max default: max description: >- Thinking intensity. Use low for lightweight reasoning, high for enhanced reasoning, or max for deep reasoning. stream: type: boolean default: false description: Streams partial response deltas over SSE when true. do_sample: type: boolean default: true description: >- Enables sampling. When false, temperature and top_p are ignored. temperature: type: number format: float minimum: 0 maximum: 1 default: 1 description: >- Sampling temperature. Adjust either temperature or top_p, not both. example: 1 top_p: type: number format: float minimum: 0 maximum: 1 default: 0.95 description: >- Nucleus sampling threshold. AnyFast accepts values from 0 to 1. example: 0.95 max_tokens: type: integer minimum: 1 maximum: 131072 default: 65536 description: Maximum generated tokens. Zhipu AI recommends at least 1024. tool_stream: type: boolean default: false description: Streams Function Call output when streaming is enabled. tools: type: array description: Function or MCP tool definitions available to the model. items: type: object properties: type: type: string example: function function: type: object properties: name: type: string description: type: string parameters: type: object additionalProperties: true tool_choice: type: string enum: - auto description: Controls tool selection. stop: type: array maxItems: 4 description: Up to four sequences that stop generation. items: type: string response_format: type: object description: Selects text or JSON object output. properties: type: type: string enum: - text - json_object default: text request_id: type: string minLength: 6 maxLength: 64 description: Client-provided unique request ID. user_id: type: string minLength: 6 maxLength: 128 description: Non-sensitive identifier for the end user. example: model: glm-5.3 messages: - role: user content: Reply with exactly OK. max_tokens: 128 responses: '200': description: Completion generated successfully content: application/json: schema: $ref: '#/components/schemas/ChatCompletion' example: id: 20260819113252725deddc07234b73 object: chat.completion created: 1787110376 model: glm-5.3 choices: - index: 0 message: role: assistant reasoning_content: >- The user requested an exact short response, so the final answer should be OK. content: OK finish_reason: stop usage: prompt_tokens: 17 completion_tokens: 91 completion_tokens_details: reasoning_tokens: 88 prompt_tokens_details: cached_tokens: 0 total_tokens: 108 '400': description: >- Invalid request, including disabled thinking or an out-of-range numeric parameter. content: application/json: schema: $ref: '#/components/schemas/Error' example: error: message: 该模型始终思考，不支持关闭思考；请使用 low、high 或 max。 type: upstream_error param: '' code: '1210' '401': description: Invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/Error' '429': description: Rate limit exceeded content: application/json: schema: $ref: '#/components/schemas/Error' components: schemas: ChatCompletion: type: object required: - id - object - created - model - choices properties: id: type: string description: Completion ID. request_id: type: string description: Request ID. object: type: string example: chat.completion created: type: integer description: Unix timestamp in seconds. model: type: string example: glm-5.3 choices: type: array items: type: object properties: index: type: integer message: type: object properties: role: type: string example: assistant content: type: string description: Final answer text. reasoning_content: type: string description: Reasoning output produced before the final answer. tool_calls: type: array items: type: object properties: id: type: string type: type: string function: type: object properties: name: type: string arguments: type: string finish_reason: type: string enum: - stop - length - tool_calls - content_filter usage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer completion_tokens_details: type: object properties: reasoning_tokens: type: integer description: Number of tokens used for reasoning. prompt_tokens_details: type: object properties: cached_tokens: type: integer description: Number of prompt tokens served from cache. total_tokens: type: integer Error: type: object properties: error: type: object properties: code: type: string message: type: string type: type: string param: type: string securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: API key ````