> ## Documentation Index > Fetch the complete documentation index at: https://docs.animusai.co/llms.txt > Use this file to discover all available pages before exploring further. # Chat Completion > Receives a series of messages as input to generate a contextually relevant chat response using a large language model (LLM). ## OpenAPI ````yaml api-reference/openapi.json post /chat/completions openapi: 3.1.0 info: version: 2.0.0 title: Animus API description: >- Animus' API provides you with a variety of AI-driven capabilities. From generating text with our advanced large language models to creating customized content schedules, our API's applications are vast and versatile. Whether it's facilitating seamless conversation through predictive response or simulating a comprehensive content calendar, our advanced functionalities can cater to an array of feature requirements. servers: - url: https://api.animusai.co/v2 security: [] paths: /chat/completions: post: tags: - Chat summary: Chat Completion description: >- Receives a series of messages as input to generate a contextually relevant chat response using a large language model (LLM). operationId: chat requestBody: required: true content: application/json: schema: type: object properties: messages: type: array description: >- A chronological list of messages that compose the current conversation. default: - content: You are having a conversation with a friend. role: system - content: Hey, what have you been up to? role: user items: type: object description: >- Each message within the conversation, attributed to either a system, user, or assistant. properties: content: type: string description: The textual content of the message. role: type: string description: >- The role or origin of the message within the conversation (e.g., user, system, assistant). enum: - user - system - assistant name: type: string description: >- A name associated with the role to help with conversational context. (e.g. Bob, Alice, etc.) temperature: type: number format: float description: >- Adjusts randomness in the response generation, with lower values yielding more predictable responses. default: 1 top_p: type: number format: float description: >- Filters the token set to those with cumulative probability above this threshold, influencing diversity. default: 1 'n': type: integer description: Number of alternate responses to generate. default: 1 max_tokens: type: integer description: >- Caps the number of tokens in the generated response. Lacks a default to allow model-specific limits. default: 150 stop: type: array items: type: string description: >- A set of strings which, when generated, signal the model to cease response generation. default: - <|im_end|> stream: type: boolean description: >- If set to true, the response is streamed back to the client as it's being generated. default: false presence_penalty: type: number format: float description: >- Adjusts likelihood of new words based on their existing presence in the text. Discourages repetition when positive. default: 1 frequency_penalty: type: number format: float description: >- Penalizes words based on their frequency in the document to encourage diversity. default: 1 best_of: type: integer description: >- Generates several completions server-side and returns the best. The definition of "best" depends on model and settings. default: 1 top_k: type: integer description: >- Limits consideration to the top k tokens, diversifying outputs by reducing predictability. default: 40 repetition_penalty: type: number format: float description: >- Modifies likelihood of repeating tokens based on their previous occurrence, counteracting model's repetition tendency. default: 1 min_p: type: number format: float description: >- Sets a minimum probability threshold for tokens to be considered for generation, further filtering the possible outputs. default: 0 length_penalty: type: number format: float description: >- Adjusts the impact of sequence length on selection, encouraging shorter or longer responses. default: 1 compliance: type: boolean description: >- When true, verifies if the response contains any violations such as inappropriate content. default: true model: type: string description: The model to use for generating the response. example: animuslabs/Vivian-llama3.1-70b-1.0-fp8 reasoning: type: boolean description: >- When true, enables reasoning/thinking content from the model. For non-streaming responses, adds a reasoning field. For streaming, thinking content appears in the stream. default: false check_image_generation: type: boolean description: >- ⚠️ ALPHA FEATURE: When true, the AI analyzes its response and creates an image_prompt field if an image is requested or desired. This feature is in alpha state and not recommended for production use. default: false tools: type: array description: >- A list of tools the model may call. Currently, only functions are supported as a tool. items: type: object properties: type: type: string enum: - function description: >- The type of the tool. Currently, only function is supported. function: type: object properties: name: type: string description: The name of the function to be called. description: type: string description: A description of what the function does. parameters: type: object description: >- The parameters the functions accepts, described as a JSON Schema object. required: - name required: - type - function tool_choice: oneOf: - type: string enum: - none - auto description: >- none means the model will not call any tool and instead generates a message. auto means the model can pick between generating a message or calling one or more tools. - type: object properties: type: type: string enum: - function function: type: object properties: name: type: string description: The name of the function to call. required: - name required: - type - function description: Controls which (if any) tool is called by the model. default: auto autoTurn: type: boolean description: >- When true, splits the API response into individual conversational turns returned as an array called 'turns'. default: false required: - messages responses: '200': description: The generated response along with relevant metadata. content: application/json: schema: type: object properties: id: type: string description: >- Unique identifier for the chat completion provided by the system. object: type: string description: >- Type indicator for the object, typically 'chat.completion'. created: type: integer description: Unix timestamp when the response was created. model: type: string description: Identifier for the model used in generating the response. choices: type: array items: type: object properties: index: type: integer description: >- Index of the choice, useful when multiple responses are generated. message: type: object properties: role: type: string description: >- Indicates the assumed role of the message, usually 'assistant'. content: type: string description: >- The generated message content intended to continue the conversation. reasoning: type: string description: >- Content extracted from ... blocks when reasoning is enabled. image_prompt: type: string description: >- ⚠️ ALPHA FEATURE: Generated image prompt when check_image_generation is enabled and AI determines an image is requested or desired. This feature is in alpha state. tool_calls: type: array description: >- The tool calls generated by the model, such as function calls. items: type: object properties: id: type: string description: The ID of the tool call. type: type: string enum: - function description: >- The type of the tool. Currently, only function is supported. function: type: object properties: name: type: string description: The name of the function to call. arguments: type: string description: >- The arguments to call the function with, as generated by the model in JSON format. required: - name - arguments required: - id - type - function turns: type: array description: >- Array of conversational turns when autoTurn is enabled. Each turn contains a portion of the response split for natural conversation flow. items: type: string description: A single conversational turn content. next: type: boolean description: >- Indicates whether there are more turns expected in the conversation when autoTurn is enabled. finish_reason: type: string description: >- The reason generation ceased, such as reaching a stop condition. compliance_violations: type: array description: >- List of detected content violations for this specific choice when compliance checking is enabled. items: type: string enum: - pedophilia - beastiality - murder - rape - incest - gore - prostitution - drug_use description: >- Contains the generated responses, along with meta-information about each. usage: type: object properties: prompt_tokens: type: integer description: Number of tokens consumed from the prompt. completion_tokens: type: integer description: Number of tokens in the generated completion. total_tokens: type: integer description: Sum of prompt and completion tokens. compliance_violations: type: array description: >- List of detected content violations when compliance checking is enabled. items: type: string enum: - pedophilia - beastiality - murder - rape - incest - gore - prostitution - drug_use example: - drug_use required: - id - object - created - choices security: - bearerAuth: [] components: securitySchemes: bearerAuth: type: http scheme: bearer ````