> ## Documentation Index > Fetch the complete documentation index at: https://docs.modelslab.com/llms.txt > Use this file to discover all available pages before exploring further. # Chat Completions > OpenAI-compatible chat completions endpoint. Works with any OpenAI SDK or compatible client. ## Request ```bash theme={null} POST https://modelslab.com/api/v7/llm/chat/completions ``` Pass your API key as a Bearer token in the `Authorization` header. ```bash theme={null} curl -X POST https://modelslab.com/api/v7/llm/chat/completions \ -H "Authorization: Bearer $MODELSLAB_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "Qwen/Qwen2.5-VL-72B-Instruct-together", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is the capital of France?"} ], "max_tokens": 1000, "temperature": 0.7 }' ``` ## Body ```json theme={null} { "model": "Qwen/Qwen2.5-VL-72B-Instruct-together", "messages": [ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "What is the capital of France?"} ], "max_tokens": 1000, "temperature": 0.7, "top_p": 1, "stream": false, "presence_penalty": 0, "frequency_penalty": 0 } ``` ## Response ```json theme={null} { "id": "chat-abc123", "object": "chat.completion", "created": 1712345678, "model": "Qwen/Qwen2.5-VL-72B-Instruct-together", "choices": [ { "index": 0, "message": { "role": "assistant", "content": "The capital of France is Paris." }, "finish_reason": "stop" } ], "usage": { "prompt_tokens": 25, "completion_tokens": 8, "total_tokens": 33 } } ``` ## Streaming Set `"stream": true` to receive Server-Sent Events (SSE) as tokens are generated: ```bash theme={null} curl -X POST https://modelslab.com/api/v7/llm/chat/completions \ -H "Authorization: Bearer $MODELSLAB_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "Qwen/Qwen2.5-VL-72B-Instruct-together", "messages": [{"role": "user", "content": "Write a haiku"}], "stream": true }' ``` Each SSE event contains a `chat.completion.chunk` object: ```json theme={null} data: {"id":"chat-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Silent"},"finish_reason":null}]} data: {"id":"chat-abc123","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":" snow"},"finish_reason":null}]} data: [DONE] ``` ## OpenAI SDK This endpoint is fully compatible with the OpenAI SDK. Just change the `base_url` and `api_key`: ```python theme={null} from openai import OpenAI client = OpenAI( api_key="YOUR_MODELSLAB_API_KEY", base_url="https://modelslab.com/api/v7/llm", ) # Non-streaming response = client.chat.completions.create( model="Qwen/Qwen2.5-VL-72B-Instruct-together", messages=[ {"role": "system", "content": "You are a helpful assistant."}, {"role": "user", "content": "Explain quantum computing in simple terms"}, ], max_tokens=1000, ) print(response.choices[0].message.content) # Streaming stream = client.chat.completions.create( model="Qwen/Qwen2.5-VL-72B-Instruct-together", messages=[{"role": "user", "content": "Write a story"}], stream=True, ) for chunk in stream: if chunk.choices[0].delta.content: print(chunk.choices[0].delta.content, end="") ``` ```javascript theme={null} import OpenAI from 'openai'; const client = new OpenAI({ apiKey: 'YOUR_MODELSLAB_API_KEY', baseURL: 'https://modelslab.com/api/v7/llm', }); const response = await client.chat.completions.create({ model: 'Qwen/Qwen2.5-VL-72B-Instruct-together', messages: [ { role: 'system', content: 'You are a helpful assistant.' }, { role: 'user', content: 'Hello!' }, ], }); console.log(response.choices[0].message.content); ``` ## OpenAPI ````yaml POST /chat/completions openapi: 3.1.0 info: title: ModelsLab LLM API description: >- Unified LLM API with OpenAI and Anthropic SDK compatibility. Access 200+ language models through a single API. version: 7.0.0 servers: [] security: [] paths: /chat/completions: post: summary: Chat Completions description: >- OpenAI-compatible chat completions endpoint. Create chat conversations and receive model responses. requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/ChatCompletionsRequest' responses: '200': description: Chat completion response content: application/json: schema: $ref: '#/components/schemas/ChatCompletionsResponse' '400': description: Bad request - invalid parameters content: application/json: schema: $ref: '#/components/schemas/Error' '401': description: Unauthorized - invalid or missing API key content: application/json: schema: $ref: '#/components/schemas/Error' security: - bearerAuth: [] servers: - url: https://modelslab.com/api/v7/llm components: schemas: ChatCompletionsRequest: type: object required: - messages properties: model: type: string description: >- Model ID to use for the completion (e.g. 'Qwen/Qwen2.5-VL-72B-Instruct-together') messages: type: array description: Array of chat messages items: $ref: '#/components/schemas/ChatMessage' max_tokens: type: integer default: 1000 minimum: 1 description: Maximum number of tokens to generate temperature: type: number minimum: 0 maximum: 2 default: 1 description: Sampling temperature (0-2). Higher values make output more random. top_p: type: number minimum: 0 maximum: 1 default: 1 description: Nucleus sampling parameter stream: type: boolean default: false description: Whether to stream partial results as Server-Sent Events presence_penalty: type: number minimum: -2 maximum: 2 default: 0 description: Penalize new tokens based on whether they appear in the text so far frequency_penalty: type: number minimum: -2 maximum: 2 default: 0 description: Penalize new tokens based on their frequency in the text so far ChatCompletionsResponse: type: object properties: id: type: string description: Unique completion ID object: type: string enum: - chat.completion created: type: integer description: Unix timestamp model: type: string description: Model used choices: type: array items: $ref: '#/components/schemas/ChatChoice' usage: $ref: '#/components/schemas/OpenAIUsage' Error: type: object properties: error: type: object properties: message: type: string type: type: string code: type: string ChatMessage: type: object required: - role - content properties: role: type: string enum: - system - user - assistant description: Role of the message sender content: type: string description: Content of the message ChatChoice: type: object properties: index: type: integer message: type: object properties: role: type: string enum: - assistant content: type: string finish_reason: type: string enum: - stop - length - content_filter OpenAIUsage: type: object properties: prompt_tokens: type: integer completion_tokens: type: integer total_tokens: type: integer securitySchemes: bearerAuth: type: http scheme: bearer description: Bearer token authentication using ModelsLab API key ````