> ## Documentation Index > Fetch the complete documentation index at: https://docs.lighton.ai/llms.txt > Use this file to discover all available pages before exploring further. # Generate a chat completion > This endpoint can be used to generate chat completions from a Large Language Model. It is a simple proxy forwarding your requests to the desired model. Any LightOn model is deployed on a vLLM-based image. **Response Types:** - When `stream=false` **(default)**: Returns a complete JSON response with all completion choices - When `stream=true`: Returns Server-Sent Events (SSE) with incremental completion chunks **Streaming Format:** Each SSE event contains a JSON object with incremental text. The stream ends with `data: [DONE]`. ## OpenAPI ````yaml /api-reference/openapi-v3.yaml post /api/v3/chat/completions openapi: 3.0.3 info: title: Paradigm API version: xenial-xerus (v3) description: >- A versatile and adaptable tool designed to integrate Generative AI into your applications servers: - url: https://paradigm.lighton.ai security: [] tags: - name: Agents description: Operations about agents - name: Threads description: Operations about agents conversation threads - name: Tools description: Operations about native tools - name: Models description: Operations about AI models - name: MCP description: Operations about MCP servers - name: Sources description: Operations about sources used by agents conversation threads - name: Artifacts description: Operations about artifacts generated by agents conversation threads - name: Agent description: >- Operations about agents (deprecated). Please use the 'Agents' API component instead. - name: Files description: Operations about files - name: Files Processing description: Operations about files processing - name: Tags description: Operations about tags - name: Workspaces description: Operations about workspaces - name: Users description: Operations about users - name: User Groups description: Operations about user groups - name: Companies description: Operations about companies - name: SCIM description: Operations about SCIM paths: /api/v3/chat/completions: post: tags: - Models summary: Generate a chat completion description: >- This endpoint can be used to generate chat completions from a Large Language Model. It is a simple proxy forwarding your requests to the desired model. Any LightOn model is deployed on a vLLM-based image. **Response Types:** - When `stream=false` **(default)**: Returns a complete JSON response with all completion choices - When `stream=true`: Returns Server-Sent Events (SSE) with incremental completion chunks **Streaming Format:** Each SSE event contains a JSON object with incremental text. The stream ends with `data: [DONE]`. operationId: api_v3_chat_completions_create requestBody: content: application/json: schema: $ref: '#/components/schemas/ChatCompletionsRequest' examples: LightOnModelExample: value: model: alfred-4.2 messages: - role: system content: You are a helpful assistant. - role: user content: Hello! summary: LightOn model example StreamingRequestExample: value: model: alfred-4.2 messages: - role: system content: You are a helpful assistant. - role: user content: Hello! stream: true summary: Streaming request example application/x-www-form-urlencoded: schema: $ref: '#/components/schemas/ChatCompletionsRequest' multipart/form-data: schema: $ref: '#/components/schemas/ChatCompletionsRequest' required: true responses: '200': content: application/json: schema: $ref: '#/components/schemas/ChatCompletionsResponse' examples: LightOnModelExample: value: model: alfred-4.2 messages: - role: system content: You are a helpful assistant. - role: user content: Hello! summary: LightOn model example StreamingRequestExample: value: model: alfred-4.2 messages: - role: system content: You are a helpful assistant. - role: user content: Hello! stream: true summary: Streaming request example description: '' security: - bearerAuth: [] components: schemas: ChatCompletionsRequest: type: object description: Request serializer for chat completions endpoint (OpenAI-compatible). properties: model: type: string description: >- Model to use for generating chat completions, must exist and be configured from the admin messages: type: array items: $ref: '#/components/schemas/ChatMessage' description: List of messages comprising the conversation so far max_tokens: type: integer description: Maximum number of tokens to generate temperature: type: number format: double description: Sampling temperature between 0 and 2 top_p: type: number format: double description: Nucleus sampling parameter 'n': type: integer description: Number of chat completion choices to generate stream: type: boolean description: Whether to stream back partial progress stop: type: array items: type: string description: Up to 4 sequences where the API will stop generating further tokens presence_penalty: type: number format: double description: >- Penalty for new tokens based on whether they appear in the text so far frequency_penalty: type: number format: double description: Penalty for new tokens based on their existing frequency in the text logit_bias: type: object additionalProperties: {} description: >- Modify the likelihood of specified tokens appearing in the completion user: type: string description: A unique identifier representing your end-user functions: type: array items: type: object additionalProperties: {} description: List of functions the model may call function_call: type: string description: Controls how the model responds to function calls required: - messages - model ChatCompletionsResponse: type: object description: Response serializer for chat completions endpoint results. properties: id: type: string description: Unique identifier for the chat completion object: type: string description: Object type, always 'chat.completion' created: type: integer description: Unix timestamp of when the chat completion was created model: type: string description: The model used for generating the chat completion choices: type: array items: $ref: '#/components/schemas/ChatCompletionChoice' description: List of chat completion choices generated by the model usage: allOf: - $ref: '#/components/schemas/CompletionUsage' description: Usage statistics for the chat completion request required: - choices - created - id - model - object ChatMessage: type: object description: Serializer for individual chat messages. properties: role: allOf: - $ref: '#/components/schemas/ChatMessageRoleEnum' description: |- The role of the message author * `system` - system * `user` - user * `assistant` - assistant * `function` - function * `tool` - tool content: oneOf: - type: string description: Plain text content - type: array items: type: object description: Structured content as a list of objects nullable: true description: The content of the message name: type: string description: Name of the message author (for function calls) function_call: type: object additionalProperties: {} description: Function call details (for assistant messages) required: - role ChatCompletionChoice: type: object description: Serializer for individual chat completion choices. properties: index: type: integer description: The index of this choice in the list of choices message: allOf: - $ref: '#/components/schemas/ChatMessageResponse' description: The chat message generated by the model finish_reason: type: string nullable: true description: The reason the model stopped generating tokens required: - index - message CompletionUsage: type: object description: Serializer for token usage information. properties: prompt_tokens: type: integer description: Number of tokens in the prompt completion_tokens: type: integer description: Number of tokens in the completion total_tokens: type: integer description: Total number of tokens used in the request required: - completion_tokens - prompt_tokens - total_tokens ChatMessageRoleEnum: enum: - system - user - assistant - function - tool type: string description: |- * `system` - system * `user` - user * `assistant` - assistant * `function` - function * `tool` - tool ChatMessageResponse: type: object description: Serializer for chat message in responses. properties: role: type: string description: The role of the message author content: type: string nullable: true description: The content of the message function_call: type: object additionalProperties: {} description: Function call details (if applicable) required: - role securitySchemes: bearerAuth: type: http scheme: bearer description: >- Bearer authentication header of the form `Bearer `, where `` is your auth token. ````