> ## Documentation Index > Fetch the complete documentation index at: https://docs2.petstoreapi.com/llms.txt > Use this file to discover all available pages before exploring further. # Create Chat Completion > Creates a model response for a chat conversation with the Pet Adoption Advisor AI. Supports streaming responses using Server-Sent Events (SSE). ## Pet Adoption Advisor Our AI assistant helps users: - Get personalized pet recommendations - Learn about pet care and adoption process - Answer questions about specific pets - Provide breed information and compatibility advice ## Streaming Mode When `stream: true`, the response is sent as Server-Sent Events (SSE), with each token delivered incrementally. This provides a better user experience for longer responses. ### Stream Format Each chunk is sent as: ``` data: {"id":"chatcmpl_abc","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hello"},"index":0}]} ``` The stream ends with: ``` data: [DONE] ``` ## Non-Streaming Mode When `stream: false` or omitted, returns a complete response object. ## OpenAPI ````yaml api-reference/modern-petstore-3.1.openapi.json post /chat/completions openapi: 3.1.0 info: title: Modern Petstore API summary: A modern, realistic pet store API demonstrating current best practices description: >- This is a modern Pet Store API based on the OpenAPI 3.2 specification. It demonstrates contemporary API design patterns and best practices including RESTful compliance, proper HTTP methods, structured error responses (RFC 9457), and modern authentication flows. Key features include pet catalog browsing, adoption workflow, order management, user accounts, AI-powered chat advisor, and real-time event notifications via webhooks. The API showcases OpenAPI 3.2 capabilities like hierarchical tags, QUERY HTTP method, OAuth device flow, and server-sent events. Some useful links: - [API Documentation](https://docs.petstoreapi.com) - [Source Code Repository](https://github.com/petstoreapi/PetstoreAPI) - [OpenAPI Specification](https://petstoreapi.com/v1/specs/modern-petstore-3.2.openapi.yaml) version: 1.0.0 contact: name: Petstore API Support url: https://petstoreapi.com/support email: support@petstoreapi.com license: name: MIT identifier: MIT servers: - url: https://api.petstoreapi.com/v1 description: Production server security: - bearerAuth: [] - oauth2: [] tags: - name: Store description: Store operations including orders and inventory - name: Pet description: Pet catalog and management operations - name: Payments description: Payment processing with polymorphic payment sources - name: User description: User account management - name: Chat description: >- AI-powered chat completions with streaming support using Server-Sent Events (SSE) externalDocs: description: Learn more about Chat API url: https://petstoreapi.com/docs/chat - name: Webhooks description: Event-driven webhook notifications (OpenAPI 3.2) externalDocs: description: Learn more about webhooks url: https://petstoreapi.com/docs/webhooks paths: /chat/completions: post: tags: - Chat summary: Create Chat Completion description: >- Creates a model response for a chat conversation with the Pet Adoption Advisor AI. Supports streaming responses using Server-Sent Events (SSE). ## Pet Adoption Advisor Our AI assistant helps users: - Get personalized pet recommendations - Learn about pet care and adoption process - Answer questions about specific pets - Provide breed information and compatibility advice ## Streaming Mode When `stream: true`, the response is sent as Server-Sent Events (SSE), with each token delivered incrementally. This provides a better user experience for longer responses. ### Stream Format Each chunk is sent as: ``` data: {"id":"chatcmpl_abc","object":"chat.completion.chunk","choices":[{"delta":{"content":"Hello"},"index":0}]} ``` The stream ends with: ``` data: [DONE] ``` ## Non-Streaming Mode When `stream: false` or omitted, returns a complete response object. operationId: createChatCompletion requestBody: required: true content: application/json: schema: type: object required: - messages properties: messages: type: array description: A list of messages comprising the conversation so far items: type: object required: - role - content properties: role: type: string enum: - SYSTEM - USER - ASSISTANT description: The role of the message author content: type: string description: The contents of the message minItems: 1 model: type: string description: ID of the model to use enum: - PET_ADVISOR_1 - PET_ADVISOR_TURBO default: PET_ADVISOR_1 stream: type: boolean description: >- If true, partial message deltas will be sent via Server-Sent Events default: true maxTokens: type: integer description: Maximum number of tokens to generate minimum: 1 maximum: 4096 default: 1024 temperature: type: number description: Sampling temperature between 0 and 2 minimum: 0 maximum: 2 default: 1 unevaluatedProperties: false examples: simple-question: summary: Simple pet question value: messages: - role: user content: What should I know before adopting a cat? model: pet-advisor-1 stream: false streaming-conversation: summary: Streaming multi-turn conversation value: messages: - role: system content: You are a helpful pet adoption advisor. - role: user content: I'm looking for a pet that's good with kids - role: assistant content: >- Great! Dogs like Labrador Retrievers and Golden Retrievers are excellent with children. - role: user content: Tell me more about Golden Retrievers model: pet-advisor-turbo stream: true temperature: 0.7 responses: '201': description: Successful response. Format depends on the `stream` parameter. headers: Content-Type: description: Response content type schema: type: string enum: - text/event-stream - application/json content: text/event-stream: schema: type: string description: >- Streaming response (when stream=true). Each line contains a JSON chunk prefixed with 'data: ' format: binary examples: streaming-response: summary: Streaming chat completion value: >+ data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1702648800,"model":"pet-advisor-1","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]} data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1702648800,"model":"pet-advisor-1","choices":[{"index":0,"delta":{"content":"Before"},"finish_reason":null}]} data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1702648800,"model":"pet-advisor-1","choices":[{"index":0,"delta":{"content":" adopting"},"finish_reason":null}]} data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1702648800,"model":"pet-advisor-1","choices":[{"index":0,"delta":{"content":" a"},"finish_reason":null}]} data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1702648800,"model":"pet-advisor-1","choices":[{"index":0,"delta":{"content":" cat"},"finish_reason":null}]} data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1702648800,"model":"pet-advisor-1","choices":[{"index":0,"delta":{"content":"..."},"finish_reason":null}]} data: {"id":"chatcmpl_abc123","object":"chat.completion.chunk","created":1702648800,"model":"pet-advisor-1","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]} data: [DONE] application/json: schema: type: object description: Non-streaming response (when stream=false) properties: id: type: string description: Unique identifier for the completion pattern: ^chatcmpl_[a-z0-9]+$ object: type: string const: chat.completion created: type: integer description: Unix timestamp of when the completion was created model: type: string description: Model used for completion choices: type: array items: type: object properties: index: type: integer message: type: object properties: role: type: string const: assistant content: type: string finishReason: type: string enum: - STOP - LENGTH - CONTENT_FILTER usage: type: object properties: promptTokens: type: integer completionTokens: type: integer totalTokens: type: integer examples: complete-response: summary: Complete chat response value: id: chatcmpl_abc123 object: chat.completion created: 1702648800 model: pet-advisor-1 choices: - index: 0 message: role: assistant content: >- Before adopting a cat, consider these important factors: 1. **Time Commitment**: Cats can live 15-20 years 2. **Space**: Ensure you have adequate living space 3. **Allergies**: Check if anyone in your household has cat allergies 4. **Costs**: Budget for food, litter, vet care, and supplies 5. **Lifestyle**: Consider if your schedule allows for proper care Would you like recommendations for cats currently available for adoption? finishReason: stop usage: promptTokens: 15 completionTokens: 89 totalTokens: 104 '400': $ref: '#/components/responses/BadRequest' '401': $ref: '#/components/responses/Unauthorized' '422': $ref: '#/components/responses/UnprocessableEntity' '429': $ref: '#/components/responses/TooManyRequests' deprecated: false security: - bearerAuth: [] - oauth2: - chat:write externalDocs: description: Complete Chat API Guide with Streaming Examples url: https://petstoreapi.com/docs/chat/streaming-guide x-codeSamples: - lang: TypeScript label: TypeScript SDK (Non-Streaming) source: |- import { PetStoreAPI } from '@petstoreapi/sdk'; const client = new PetStoreAPI({ accessToken: process.env.OAUTH_ACCESS_TOKEN }); const completion = await client.chat.completions.create({ messages: [ { role: 'user', content: 'What should I know before adopting a cat?' } ], model: 'pet-advisor-1', stream: false }); console.log(completion.choices[0].message.content); - lang: TypeScript label: TypeScript SDK (Streaming) source: |- import { PetStoreAPI } from '@petstoreapi/sdk'; const client = new PetStoreAPI({ accessToken: process.env.OAUTH_ACCESS_TOKEN }); const stream = await client.chat.completions.create({ messages: [ { role: 'user', content: 'What should I know before adopting a cat?' } ], model: 'pet-advisor-1', stream: true }); for await (const chunk of stream) { const content = chunk.choices[0]?.delta?.content; if (content) { process.stdout.write(content); } } - lang: Python label: Python (Streaming) source: |- from petstore import PetStoreAPI client = PetStoreAPI(access_token=os.environ['OAUTH_ACCESS_TOKEN']) stream = client.chat.completions.create( messages=[ {"role": "user", "content": "What should I know before adopting a cat?"} ], model="pet-advisor-1", stream=True ) for chunk in stream: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="") - lang: JavaScript label: JavaScript (Fetch with SSE) source: |- const response = await fetch( 'https://api.petstoreapi.com/v1/chat/completions', { method: 'POST', headers: { 'Authorization': `Bearer ${accessToken}`, 'Content-Type': 'application/json' }, body: JSON.stringify({ messages: [ { role: 'user', content: 'What should I know before adopting a cat?' } ], model: 'pet-advisor-1', stream: true }) } ); const reader = response.body.getReader(); const decoder = new TextDecoder(); while (true) { const { value, done } = await reader.read(); if (done) break; const chunk = decoder.decode(value); const lines = chunk.split('\n').filter(line => line.startsWith('data: ')); for (const line of lines) { const data = line.replace('data: ', ''); if (data === '[DONE]') break; const parsed = JSON.parse(data); process.stdout.write(parsed.choices[0]?.delta?.content || ''); } } - lang: Shell label: cURL (Non-Streaming) source: |- curl -X POST 'https://api.petstoreapi.com/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_ACCESS_TOKEN' \ -H 'Content-Type: application/json' \ -d '{ "messages": [ { "role": "user", "content": "What should I know before adopting a cat?" } ], "model": "pet-advisor-1", "stream": false }' components: responses: BadRequest: description: Bad request - Invalid parameters headers: RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: $ref: '#/components/headers/RateLimit-Remaining' RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' content: application/problem+json: schema: $ref: '#/components/schemas/Error' examples: invalid-parameter: summary: Invalid query parameter value: type: https://petstoreapi.com/errors/bad-request title: Bad Request status: 400 detail: >- Invalid value for parameter 'status'. Must be one of: available, pending, sold. instance: /pets Unauthorized: description: Unauthorized - Authentication required content: application/problem+json: schema: $ref: '#/components/schemas/Error' examples: missing-token: summary: Missing authentication token value: type: https://petstoreapi.com/errors/unauthorized title: Unauthorized status: 401 detail: >- Authentication is required to access this resource. Please provide a valid OAuth 2.0 token. UnprocessableEntity: description: Unprocessable entity - Validation errors content: application/problem+json: schema: $ref: '#/components/schemas/Error' examples: validation-errors: summary: Validation errors value: type: https://petstoreapi.com/errors/validation-error title: Validation Error status: 422 detail: The request body contains validation errors. instance: /pets errors: - field: name message: Pet name is required code: required_field - field: status message: Invalid status value code: invalid_format TooManyRequests: description: Too many requests - Rate limit exceeded headers: RateLimit-Limit: $ref: '#/components/headers/RateLimit-Limit' RateLimit-Remaining: schema: type: integer example: 0 RateLimit-Reset: $ref: '#/components/headers/RateLimit-Reset' Retry-After: description: Number of seconds to wait before retrying schema: type: integer example: 60 content: application/problem+json: schema: $ref: '#/components/schemas/Error' examples: rate-limit-exceeded: summary: Rate limit exceeded value: type: https://petstoreapi.com/errors/rate-limit-exceeded title: Too Many Requests status: 429 detail: >- Rate limit exceeded. Please wait 60 seconds before making another request. headers: RateLimit-Limit: description: The maximum number of requests allowed in the current time window schema: type: integer example: 100 RateLimit-Remaining: description: The number of requests remaining in the current time window schema: type: integer example: 95 RateLimit-Reset: description: The time at which the current rate limit window resets (Unix timestamp) schema: type: integer example: 1702648800 schemas: Error: type: object description: RFC 9457 Problem Details for HTTP APIs required: - type - title - status properties: type: type: string format: uri description: A URI reference that identifies the problem type examples: - https://petstoreapi.com/errors/not-found - https://petstoreapi.com/errors/validation-error title: type: string description: A short, human-readable summary of the problem examples: - Resource Not Found - Validation Error status: type: integer description: The HTTP status code examples: - 404 - 400 - 422 detail: type: string description: A human-readable explanation specific to this occurrence examples: - The requested pet with ID '123' was not found instance: type: string format: uri description: A URI reference that identifies the specific occurrence examples: - /v1/pets/123 errors: type: array description: Detailed validation errors (for 422 responses) items: type: object required: - field - message properties: field: type: string description: The field that failed validation message: type: string description: Description of the validation error code: type: string description: Machine-readable error code unevaluatedProperties: false unevaluatedProperties: false securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: >- Bearer token authentication using JWT (JSON Web Token). Include the token in the Authorization header as: `Authorization: Bearer ` oauth2: type: oauth2 description: >- OAuth 2.0 authorization with multiple flows including device authorization for IoT devices and smart TVs flows: authorizationCode: authorizationUrl: https://auth.petstoreapi.com/authorize tokenUrl: https://auth.petstoreapi.com/token refreshUrl: https://auth.petstoreapi.com/refresh scopes: read:pets: Read pet information write:pets: Create and update pets read:orders: Read order information write:orders: Create and manage orders read:user: Read user profile write:user: Update user profile chat:write: Access AI chat completions ````