> ## Documentation Index > Fetch the complete documentation index at: https://docs.shuyou.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create Chat Completion > Create a chat completion using the OpenAI-compatible Chat Completions API. ## OpenAPI ````yaml en/api-reference/language-series/openai/create-chat-completion.json POST /v1/chat/completions openapi: 3.1.0 info: title: Create Chat Completion version: 1.0.0 servers: - url: https://api.shuyou.ai security: - bearerAuth: [] paths: /v1/chat/completions: post: tags: - OpenAI Compatible API summary: Create Chat Completion operationId: createChatCompletion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' examples: simple: summary: Simple chat value: model: openai/gpt-5.5-pro messages: - role: developer content: You are a helpful assistant. - role: user content: Hello! stream: summary: Streaming value: model: openai/gpt-5.5-pro messages: - role: user content: Hello! stream: true tools: summary: Function calling value: model: openai/gpt-5.5-pro messages: - role: user content: What is the weather like in Boston today? tools: - type: function function: name: get_current_weather description: Get the current weather in a given location parameters: type: object properties: location: type: string description: The city and state, e.g. San Francisco, CA unit: type: string enum: - celsius - fahrenheit required: - location tool_choice: auto vision: summary: Vision (multimodal) value: model: openai/gpt-5.5-pro messages: - role: user content: - type: text text: What is in this image? - type: image_url image_url: url: >- https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg detail: auto max_completion_tokens: 300 responses: '200': description: Chat completion object, or SSE stream when `stream` is true content: application/json: schema: $ref: '#/components/schemas/ChatCompletion' example: id: chatcmpl-example object: chat.completion created: 1741569952 model: openai/gpt-5.5-pro choices: - index: 0 message: role: assistant content: Hello! How can I assist you today? refusal: null annotations: [] logprobs: null finish_reason: stop usage: prompt_tokens: 19 completion_tokens: 10 total_tokens: 29 prompt_tokens_details: cached_tokens: 0 audio_tokens: 0 completion_tokens_details: reasoning_tokens: 0 audio_tokens: 0 accepted_prediction_tokens: 0 rejected_prediction_tokens: 0 '400': description: Invalid request '401': description: Unauthorized '429': description: Rate limit exceeded components: schemas: ChatCompletionRequest: type: object required: - model - messages properties: messages: type: array description: >- A list of messages comprising the conversation so far. Supports text, images, audio, and file content parts depending on the model. items: $ref: '#/components/schemas/ChatCompletionMessageParam' minItems: 1 model: type: string description: Model ID (`provider/model_name`). Use the `slug` from List Models. example: openai/gpt-5.5-pro max_completion_tokens: type: integer nullable: true description: >- Upper bound for generated tokens, including visible output and reasoning tokens. temperature: type: number minimum: 0 maximum: 2 default: 1 description: >- Sampling temperature. Higher values are more random; lower values are more deterministic. top_p: type: number minimum: 0 maximum: 1 default: 1 description: >- Nucleus sampling: only tokens within the top_p probability mass are considered. 'n': type: integer minimum: 1 maximum: 128 default: 1 description: >- Number of chat completion choices per input message. ShuYou currently supports `n=1` only. frequency_penalty: type: number minimum: -2 maximum: 2 default: 0 description: Penalize tokens based on existing frequency in the text so far. presence_penalty: type: number minimum: -2 maximum: 2 default: 0 description: Penalize tokens based on whether they appear in the text so far. stop: oneOf: - type: string - type: array items: type: string maxItems: 4 nullable: true description: >- Up to 4 sequences where the API stops generating. Not supported on some reasoning models. logit_bias: type: object additionalProperties: type: number minimum: -100 maximum: 100 description: Maps token IDs to bias values (-100 to 100) applied before sampling. logprobs: type: boolean nullable: true default: false description: Return log probabilities of output tokens. top_logprobs: type: integer minimum: 0 maximum: 20 description: >- Number of most likely tokens per position. Requires `logprobs: true`. tools: type: array description: Tools the model may call (function or custom tools). items: $ref: '#/components/schemas/ChatCompletionTool' tool_choice: oneOf: - type: string enum: - none - auto - required - $ref: '#/components/schemas/ChatCompletionNamedToolChoice' - $ref: '#/components/schemas/ChatCompletionAllowedToolChoice' description: >- Controls which tool(s) the model calls. Default: `auto` when tools are present, else `none`. parallel_tool_calls: type: boolean default: true description: Whether to allow parallel tool calls in a single response. reasoning_effort: type: string enum: - none - minimal - low - medium - high - xhigh description: >- Reasoning effort for reasoning models. Supported values vary by model. verbosity: type: string enum: - low - medium - high description: Constrains response verbosity. web_search_options: type: object description: Configuration for the web search tool. properties: search_context_size: type: string enum: - low - medium - high description: 'Amount of context window space for search. Default: `medium`.' user_location: type: object properties: type: type: string enum: - approximate approximate: type: object properties: city: type: string country: type: string description: Two-letter ISO country code region: type: string timezone: type: string description: IANA timezone metadata: type: object additionalProperties: type: string maxLength: 512 description: >- Up to 16 key-value pairs (keys max 64 chars) for structured metadata. response_format: oneOf: - $ref: '#/components/schemas/ResponseFormatText' - $ref: '#/components/schemas/ResponseFormatJSONObject' - $ref: '#/components/schemas/ResponseFormatJSONSchema' description: 'Output format: `text`, `json_object`, or structured `json_schema`.' stream: type: boolean nullable: true default: false description: Stream the response via server-sent events. stream_options: type: object description: Options when `stream` is true. properties: include_usage: type: boolean description: Include a final chunk with token usage before `[DONE]`. include_obfuscation: type: boolean description: Include obfuscation fields on streaming deltas. reasoning: type: object description: 'ShuYou: configure reasoning trace behavior.' properties: enabled: type: boolean effort: type: string enum: - low - medium - high max_tokens: type: number exclude: type: boolean usage: type: object properties: include: type: boolean required: - include required: - enabled provider: type: object description: 'ShuYou: multi-provider routing configuration.' properties: routing: $ref: '#/components/schemas/ProviderRouting' fallback: type: string required: - routing model_routing_config: type: object description: 'ShuYou: model selection within a provider.' properties: available_models: type: array items: type: string preference: type: string task_info: type: object properties: task_type: type: string enum: - chat - completion - embedding complexity: type: string enum: - low - medium - high required: - available_models ChatCompletion: type: object properties: id: type: string object: type: string enum: - chat.completion created: type: integer description: Unix timestamp (seconds). model: type: string choices: type: array items: $ref: '#/components/schemas/ChatCompletionChoice' usage: $ref: '#/components/schemas/CompletionUsage' system_fingerprint: type: string ChatCompletionMessageParam: type: object required: - role properties: role: type: string enum: - developer - system - user - assistant - tool description: Message author role. content: oneOf: - type: string - type: array items: $ref: '#/components/schemas/ChatCompletionContentPart' description: Message content as text or multimodal content parts. name: type: string description: Optional participant name to distinguish same-role participants. tool_call_id: type: string description: >- Required for `tool` role: ID of the tool call this message responds to. tool_calls: type: array items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' description: Tool calls generated by the assistant. refusal: type: string nullable: true description: Assistant refusal message. reasoning: type: string description: Reasoning text when reasoning is enabled (pass back in multi-turn). reasoning_details: type: array description: >- Detailed reasoning segments; pass back unchanged in multi-turn tool calls. items: type: object properties: type: type: string text: type: string signature: type: string format: type: string index: type: number ChatCompletionTool: oneOf: - $ref: '#/components/schemas/ChatCompletionFunctionTool' - $ref: '#/components/schemas/ChatCompletionCustomTool' ChatCompletionNamedToolChoice: type: object required: - type properties: type: type: string enum: - function - custom function: type: object properties: name: type: string required: - name custom: type: object properties: name: type: string required: - name ChatCompletionAllowedToolChoice: type: object required: - type - allowed_tools properties: type: type: string enum: - allowed_tools allowed_tools: type: object properties: mode: type: string enum: - auto - required tools: type: array items: type: object ResponseFormatText: type: object required: - type properties: type: type: string enum: - text ResponseFormatJSONObject: type: object required: - type properties: type: type: string enum: - json_object ResponseFormatJSONSchema: type: object required: - type - json_schema properties: type: type: string enum: - json_schema json_schema: type: object required: - name properties: name: type: string maxLength: 64 description: type: string schema: type: object strict: type: boolean ProviderRouting: type: object required: - type - providers properties: type: type: string enum: - priority - round_robin - least_latency description: Routing strategy across providers. primary_factor: type: string enum: - cost - speed - quality providers: type: array items: type: string example: - openai - anthropic - google ChatCompletionChoice: type: object properties: index: type: integer message: $ref: '#/components/schemas/ChatCompletionMessage' finish_reason: type: string enum: - stop - length - tool_calls - content_filter - function_call logprobs: type: object nullable: true CompletionUsage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer prompt_tokens_details: type: object properties: cached_tokens: type: integer audio_tokens: type: integer completion_tokens_details: type: object properties: reasoning_tokens: type: integer audio_tokens: type: integer accepted_prediction_tokens: type: integer rejected_prediction_tokens: type: integer ChatCompletionContentPart: oneOf: - $ref: '#/components/schemas/ContentPartText' - $ref: '#/components/schemas/ContentPartImage' - $ref: '#/components/schemas/ContentPartInputAudio' - $ref: '#/components/schemas/ContentPartFile' - $ref: '#/components/schemas/ContentPartRefusal' ChatCompletionMessageToolCall: oneOf: - $ref: '#/components/schemas/FunctionToolCall' - $ref: '#/components/schemas/CustomToolCall' ChatCompletionFunctionTool: type: object required: - type - function properties: type: type: string enum: - function function: $ref: '#/components/schemas/FunctionDefinition' ChatCompletionCustomTool: type: object required: - type - custom properties: type: type: string enum: - custom custom: type: object required: - name properties: name: type: string description: type: string format: oneOf: - type: object properties: type: enum: - text - type: object properties: type: enum: - grammar grammar: type: object properties: definition: type: string syntax: type: string enum: - lark - regex ChatCompletionMessage: type: object properties: role: type: string enum: - assistant content: type: string nullable: true refusal: type: string nullable: true tool_calls: type: array items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' annotations: type: array items: type: object reasoning: type: string reasoning_details: type: array items: type: object ContentPartText: type: object required: - type - text properties: type: type: string enum: - text text: type: string ContentPartImage: type: object required: - type - image_url properties: type: type: string enum: - image_url image_url: type: object required: - url properties: url: type: string description: Image URL or base64 data URL. detail: type: string enum: - auto - low - high ContentPartInputAudio: type: object required: - type - input_audio properties: type: type: string enum: - input_audio input_audio: type: object required: - data - format properties: data: type: string description: Base64-encoded audio. format: type: string enum: - wav - mp3 ContentPartFile: type: object required: - type - file properties: type: type: string enum: - file file: type: object properties: file_id: type: string file_data: type: string description: Base64-encoded file data. filename: type: string ContentPartRefusal: type: object required: - type - refusal properties: type: type: string enum: - refusal refusal: type: string FunctionToolCall: type: object required: - id - type - function properties: id: type: string type: type: string enum: - function function: type: object properties: name: type: string arguments: type: string description: JSON string of arguments. CustomToolCall: type: object required: - id - type - custom properties: id: type: string type: type: string enum: - custom custom: type: object properties: name: type: string input: type: string FunctionDefinition: type: object required: - name properties: name: type: string maxLength: 64 description: type: string parameters: type: object description: JSON Schema for function parameters. strict: type: boolean description: Enable strict schema adherence for function calls. securitySchemes: bearerAuth: type: http scheme: bearer description: '`Authorization: Bearer YOUR_API_KEY`' ````