> ## Documentation Index > Fetch the complete documentation index at: https://docs.waystone.run/llms.txt > Use this file to discover all available pages before exploring further. # Create chat completion > Send a chat completion request ## OpenAPI ````yaml post /api/gateway/v1/chat/completions openapi: 3.1.0 info: title: Waystone API description: Development documentation version: 1.0.0 servers: - url: http://localhost:3000 description: Local server security: - bearerAuth: [] paths: /api/gateway/v1/chat/completions: post: summary: Create chat completion description: Send a chat completion request operationId: postApiGatewayV1ChatCompletions parameters: [] requestBody: content: application/json: schema: allOf: - type: object properties: model: type: string examples: - openai/gpt-4o-mini - gpt-4o-mini description: >- / to use in the query. If is unique across providers, can supply only metadata: type: object properties: waystone: type: string additionalProperties: type: string description: >- Key-value pairs of metadata for the request. Identify end-users associated with the query with the `waystone` metadata. All other fields are metadata for OpenAI requests and are not used by Waystone. examples: - waystone: "{\n\t\t\t\t\t\t\"user\": {\n\t\t\t\t\t\t\t\"id\": \"user123\",\n\t\t\t\t\t\t\t\"metadata\": { \"email\": \"user@example.com\", \"name\": \"John Doe\" }\n\t\t\t\t\t\t}\n\t\t\t\t\t}" - waystone: "{\n\t\t\t\t\t\t\"user\": \"user123\",\n\t\t\t\t\t\t\"group\": { \"id\": \"group123\", \"metadata\": { \"name\": \"Group Name\" } }\n\t\t\t\t\t}" store: type: - boolean - 'null' default: false description: >- For OpenAI: Whether or not to store the output of this chat completion request in OpenAI required: - model - type: object properties: stream: type: - boolean - 'null' default: false description: >- If set to true, the model response data will be streamed to the client as it is generated user: type: string description: >- For OpenAI: A unique identifier representing your end-user. NOT used by Waystone. temperature: type: number default: 1 maximum: 2 minimum: 0 description: >- What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both. frequency_penalty: type: number default: 0 maximum: 2 minimum: -2 description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. max_completion_tokens: type: number description: >- An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. 'n': type: number default: 1 description: >- How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs. - type: object properties: messages: type: array items: anyOf: - type: object properties: content: anyOf: - type: string - type: array items: type: string description: The contents of the system message. role: type: string enum: - developer - system - user - assistant - function name: type: string description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role - type: object properties: content: type: string description: The contents of the tool message. role: type: string const: tool tool_call_id: type: string required: - content - role - tool_call_id description: A list of messages comprising the conversation so far. required: - messages responses: '200': description: Successful response content: application/json: schema: type: object properties: choices: type: array items: type: object properties: finish_reason: type: string description: >- The reason the model stopped generating tokens. This will be stop if the model hit a natural stop point or a provided stop sequence, length if the maximum number of tokens specified in the request was reached, content_filter if content was omitted due to a flag from our content filters, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function. index: type: number description: The index of the choice in the list of choices. logprobs: type: - object - 'null' description: Log probability information for the choice. message: type: object properties: contents: type: - string - 'null' refusal: type: - string - 'null' description: The refusal message generated by the model. role: type: string annotations: type: array items: type: object description: >- Annotations for the message, when applicable, as when using the web search tool. audio: type: - object - 'null' description: >- If the audio output modality is requested, this object contains data about the audio response from the model. required: - contents - refusal - role - annotations - audio description: A chat completion message generated by the model. created: type: number description: >- The Unix timestamp (in seconds) of when the chat completion was created. required: - finish_reason - index - logprobs - message - created minItems: 1 id: type: string description: >- The unique identifier for the chat completion, generated by the model provider. object: type: string model: type: string description: The model name used to generate the response. usage: type: object properties: completion_tokens: type: number prompt_tokens: type: number total_tokens: type: number completion_tokens_details: type: object prompt_tokens_details: type: object required: - choices - id - object - model - usage components: securitySchemes: bearerAuth: type: http scheme: bearer ````