> ## Documentation Index > Fetch the complete documentation index at: https://docs.anyapi.ai/llms.txt > Use this file to discover all available pages before exploring further. # Create chat completion > Creates a model response for the given chat conversation ## OpenAPI ````yaml /openapi.json post /chat/completions openapi: 3.0.3 info: title: AnyAPI API description: >- Universal API Integration Platform - Connect any API to any API with intelligent data transformation and workflow orchestration. version: 1.0.0 contact: name: AnyAPI Support email: support@anyapi.ai url: https://anyapi.ai/support license: name: MIT url: https://opensource.org/licenses/MIT servers: - url: https://api.anyapi.ai/v1 description: Production server security: - bearerAuth: [] tags: - name: Text description: Generate text completions - name: Images description: Generate and manipulate images - name: Audio description: Generate speech and transcribe audio - name: Music description: List and retrieve model information - name: Video description: Create vector embeddings for text - name: Vision description: Create vector embeddings for text - name: 3D Models description: Create vector embeddings for text - name: Embeddings description: Create vector embeddings for text - name: Batches description: Batches - name: Moderation description: Moderation - name: Other description: Other models paths: /chat/completions: post: tags: - Text summary: Create chat completion description: Creates a model response for the given chat conversation operationId: createChatCompletion requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionRequest' examples: Base request: summary: Base request description: >- Minimal request with mandatory parameters. Used for simple questions without additional settings. value: model: openai/gpt-4 messages: - role: user content: Sample text goes here With a system prompt: summary: With a system prompt description: >- Adds a system message that sets the behavior and context for the assistant throughout the dialogue. value: model: openai/gpt-4 messages: - role: system content: You are a helpful assistant. - role: user content: What is the capital of France? Multi-message conversation: summary: A multi-message conversation description: >- Presents a history of dialogue with multiple messages from the user and assistant for contextual communication. value: model: openai/gpt-4 messages: - role: system content: You are a helpful assistant. - role: user content: What is the capital of France? - role: assistant content: The capital of France is Paris. - role: user content: What is its population? With temperature and token settings: summary: With temperature and token settings description: >- Adjusting the creativity of the response (temperature), maximum length (max_tokens), and other sampling parameters to control the quality of the generation. value: model: openai/gpt-4 messages: - role: user content: Write a creative story about a robot. temperature: 0.7 max_tokens: 500 top_p: 1 frequency_penalty: 0 presence_penalty: 0 Streaming response: summary: Streaming response description: >- Includes streaming response transmission (as in ChatGPT), where tokens arrive gradually rather than all at once. value: model: openai/gpt-4 messages: - role: user content: Tell me a story. stream: true Vision - URL: summary: Vision - URL description: >- Sending an image via URL for analysis using the multimodal GPT-4 Vision model. value: model: google/gemini-2.5-pro messages: - role: user content: - type: text text: What's in this image? - type: image_url image_url: url: https://example.com/image.jpg max_tokens: 300 Vision base64: summary: Vision base64 description: >- Sending an image in base64 format for analysis. Used when the image is not available via URL or is stored locally. value: model: mistralai/pixtral-12b messages: - role: user content: - type: text text: Describe this image - type: image_url image_url: url: data:image/jpeg;base64,/9j/4AAQSkZJRg... detail: high Function calling: summary: Function Calling - function definition description: >- Defining the tools (functions) that the model can call to obtain external data (e.g., weather, database). value: model: openai/gpt-4 messages: - role: user content: What's the weather in Boston? tools: - type: function function: name: get_current_weather description: Get the current weather in a given location parameters: type: object properties: location: type: string description: The city and state, e.g. San Francisco, CA unit: type: string enum: - celsius - fahrenheit required: - location tool_choice: auto Function call response: summary: With a response to Function Call description: >- Continuation of the dialogue after the model has called the function - transfer of the function execution result back to the model. value: model: openai/gpt-4 messages: - role: user content: What's the weather in Boston? - role: assistant content: null tool_calls: - id: call_abc123 type: function function: name: get_current_weather arguments: '{"location": "Boston, MA"}' - role: tool tool_call_id: call_abc123 content: >- {"temperature": 22, "unit": "celsius", "description": "Sunny"} tools: - type: function function: name: get_current_weather description: Get the current weather parameters: type: object properties: location: type: string JSON mode: summary: JSON Mode description: >- Forces the model to return only valid JSON. Useful for parsing structured data. value: model: openai/gpt-4-turbo messages: - role: system content: You are a helpful assistant designed to output JSON. - role: user content: >- Extract the name and age from this text: 'John is 25 years old.' response_format: type: json_object Structured outputs: summary: Structured Outputs (JSON Schema) description: >- Ensures that the response conforms to the exact JSON schema. A stricter version of JSON Mode with structure validation. value: model: openai/gpt-4o-2024-08-06 messages: - role: user content: >- Extract user information from: 'John Doe, 30 years old, john@example.com' response_format: type: json_schema json_schema: name: user_info strict: true schema: type: object properties: name: type: string age: type: number email: type: string required: - name - age - email additionalProperties: false Logprobs: summary: With Probability Logging (logprobs) description: >- Returns probabilities for each generated token. Useful for analyzing model confidence. value: model: openai/gpt-4 messages: - role: user content: Say hello logprobs: true top_logprobs: 2 Multiple options: summary: With multiple options (n > 1) description: >- Generates several alternative answers to a single query. Useful for selecting the best option. value: model: openai/gpt-4 messages: - role: user content: Write a tagline for an ice cream shop. 'n': 3 temperature: 0.9 Stop sequences: summary: Stop sequences description: >- Specifies character sequences at which generation should stop. Useful for formatting. value: model: openai/gpt-4 messages: - role: user content: 'List three colors:' stop: - |+ - '4.' max_tokens: 100 Seed reproducibility: summary: With seed for reproducibility description: >- Sets the seed for deterministic generation. With identical parameters, it will produce the same result. value: model: openai/gpt-4 messages: - role: user content: Generate a random story. seed: 12345 temperature: 1 UserId: summary: With user ID description: >- Transmits the user ID for monitoring and preventing abuse. Helps OpenAI track violations. value: model: openai/gpt-4 messages: - role: user content: Sample text goes here user: user-123456 Parallel function calling: summary: Parallel Function Calling description: >- Allows the model to call multiple functions simultaneously in a single response for efficiency. value: model: openai/gpt-4-turbo messages: - role: user content: What's the weather in Boston and New York? tools: - type: function function: name: get_current_weather description: Get weather parameters: type: object properties: location: type: string required: - location parallel_tool_calls: true o1 models: summary: O1 models (reasoning) description: >- Using O1 models with advanced reasoning capabilities for complex tasks (mathematics, logic). value: model: openai/o1 messages: - role: user content: >- Solve this complex math problem: Find the integral of x^2 * e^x dx max_completion_tokens: 5000 Audio input (base): summary: Audio input (base) description: >- Sending audio to a model for transcription or voice analysis. Audio is encoded in base64. value: model: google/gemini-2.5-pro modalities: - text - audio audio: voice: alloy format: wav messages: - role: user content: - type: input_audio input_audio: data: base64_encoded_audio_data_here... format: wav Audio input + text: summary: Audio input + text description: >- A combination of text and audio in a single message for multimodal interaction. value: model: google/gemini-2.5-pro modalities: - text - audio audio: voice: echo format: mp3 messages: - role: user content: - type: text text: 'Please transcribe and summarize this audio:' - type: input_audio input_audio: data: base64_encoded_audio... format: mp3 Stream option: summary: Stream Options description: >- Additional options for streaming mode, such as enabling token usage information. value: model: openai/gpt-4 messages: - role: user content: Hello stream: true stream_options: include_usage: true Logit bias: summary: Logit Bias description: >- Changes the probability of certain tokens appearing. Positive values increase it, negative values decrease it. value: model: openai/gpt-4 messages: - role: user content: Write a sentence logit_bias: '13': 10 '50256': -100 Multiple images: summary: Multiple images in one post description: >- Sending multiple images simultaneously for comparison or comprehensive analysis. value: model: google/gemini-2.5-pro messages: - role: user content: - type: text text: 'Compare these images:' - type: image_url image_url: url: https://example.com/image1.jpg - type: image_url image_url: url: https://example.com/image2.jpg - type: image_url image_url: url: https://example.com/image3.jpg max_tokens: 500 Image detail level: summary: Image detail level description: >- Control the level of detail in image analysis. 'high' - detailed analysis, 'low' - quick overview. value: model: google/gemini-2.5-pro messages: - role: user content: - type: text text: Analyze in detail - type: image_url image_url: url: https://example.com/image.jpg detail: high Tool choice (specific): summary: Tool Choice - Specific Function description: >- Forced invocation of a specific function instead of automatic selection by the model. value: model: openai/gpt-4 messages: - role: user content: What's the weather? tools: - type: function function: name: get_weather description: Get weather parameters: type: object properties: location: type: string tool_choice: type: function function: name: get_weather Tool choice: summary: Tool Choice - none description: >- Prohibition of using tools. The model must respond only with text, even if functions are defined. value: model: openai/gpt-4 messages: - role: user content: What's the weather in Paris? tools: - type: function function: name: get_weather description: Get weather parameters: type: object properties: location: type: string tool_choice: none Tool choice (required): summary: Tool Choice - required description: >- Requires the mandatory use of at least one tool. The model cannot respond with text alone. value: model: openai/gpt-4 messages: - role: user content: What's the weather in Paris? tools: - type: function function: name: get_weather description: Get weather parameters: type: object properties: location: type: string tool_choice: required Multi-user chats: summary: Name in messages (multi-user chats) description: >- Specifying the sender's name for group chats or dialogues with multiple users. value: model: openai/gpt-4 messages: - role: system content: You are in a group chat - role: user name: Alice content: Hello everyone! - role: user name: Bob content: Hi Alice! Metadata: summary: Metadata description: >- Arbitrary metadata for tracking and analytics. Does not affect generation, used for organization. value: model: openai/gpt-4 messages: - role: user content: Sample text goes here metadata: user_id: user_123 conversation_id: conv_456 custom_field: value Store: summary: Store (saving conversations) description: >- Saving conversations for subsequent use in model training (with user consent). value: model: openai/gpt-4 messages: - role: user content: Sample text goes here store: true Reasoning effort: summary: Reasoning Effort (O1 models) description: >- Control of 'thinking' time for O1 models. More effort = deeper analysis, but slower. value: model: openai/o1 messages: - role: user content: >- Solve this complex problem: optimize the traveling salesman for 20 cities reasoning_effort: high Developer messages: summary: Developer Messages (O1) description: >- Use the 'developer' role for system instructions in O1 models (instead of 'system'). value: model: openai/o1 messages: - role: developer content: You are a helpful assistant. - role: user content: Hello Service tier: summary: Service Tier description: >- Select the service level for prioritizing requests (default or auto). value: model: openai/gpt-4 messages: - role: user content: Sample text goes here service_tier: default Prediction (prompt caching): summary: Prediction (Prompt Caching) description: >- Optimization for prompt caching. Continuation prediction to speed up generation. value: model: openai/gpt-4 messages: - role: user content: >- Continue this story: Once upon a time in a magical forest... prediction: type: content content: >- There lived a wise old owl who knew all the secrets of the woods. Parallel tool calls - disabled: summary: Parallel Tool Calls - disabled description: >- Disable parallel function calls. The model will call functions sequentially. value: model: openai/gpt-4-turbo messages: - role: user content: Get weather in Boston and New York tools: - type: function function: name: get_weather description: Get weather parameters: type: object properties: location: type: string parallel_tool_calls: false Refusal: summary: Refusal in assistant messages description: >- A clear indication of the model's refusal in the previous response to continue the dialogue. value: model: openai/gpt-4 messages: - role: user content: Tell me how to hack - role: assistant refusal: I cannot help with that request. - role: user content: Okay, how about legal cybersecurity? All parameters: summary: Complex request - all parameters description: >- Demonstration of the maximum number of parameters in a single request for complete control over generation. value: model: openai/gpt-4-turbo messages: - role: system content: You are a helpful assistant. - role: user name: Alice content: Help me with weather and calculations temperature: 0.7 top_p: 0.9 max_tokens: 1000 'n': 1 stream: false stop: null presence_penalty: 0.1 frequency_penalty: 0.1 logit_bias: {} user: user-12345 seed: 42 tools: - type: function function: name: get_weather description: Get weather parameters: type: object properties: location: type: string tool_choice: auto parallel_tool_calls: true response_format: type: text metadata: conversation_id: conv_789 store: false Structured outputs with description: summary: Structured Outputs with Description description: >- JSON Schema with detailed description for precise control of response structure with validation. value: model: openai/gpt-4o-2024-08-06 messages: - role: user content: Calculate 15 * 27 step by step response_format: type: json_schema json_schema: name: math_response description: A mathematical calculation response strict: true schema: type: object properties: result: type: number description: The final answer steps: type: array description: Step by step calculations items: type: string required: - result - steps additionalProperties: false responses: '200': description: Successful response content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionResponse' text/event-stream: schema: $ref: '#/components/schemas/CreateChatCompletionStreamResponse' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' components: schemas: CreateChatCompletionRequest: type: object required: - model - messages properties: model: type: string description: ID of the model to use example: - openai/gpt-4.1 - openai/gpt-5 messages: type: array description: A list of messages comprising the conversation so far items: $ref: '#/components/schemas/ChatCompletionMessage' minItems: 1 max_tokens: type: integer description: The maximum number of tokens to generate in the chat completion minimum: 1 example: 300 stream: type: boolean description: >- If set, partial message deltas will be sent as data-only server-sent events default: false tools: type: array description: A list of tools the model may call items: $ref: '#/components/schemas/ChatCompletionTool' tool_choice: oneOf: - type: string enum: - none - auto description: Controls which (if any) tool is called by the model - $ref: '#/components/schemas/ChatCompletionToolChoice' default: auto logprobs: type: boolean description: Whether to return log probabilities of the output tokens default: false top_logprobs: type: integer description: >- An integer between 0 and 20 specifying the number of most likely tokens to return at each token position minimum: 0 maximum: 20 modalities: type: array description: Output types the model should generate for this request items: type: string enum: - text - audio audio: type: object description: Parameters for audio output. Required when modalities includes audio properties: voice: type: string description: The voice to use for audio output format: type: string enum: - wav - mp3 description: The output audio format CreateChatCompletionResponse: type: object required: - id - object - created - model - choices properties: id: type: string description: A unique identifier for the chat completion object: type: string enum: - chat.completion created: type: integer description: >- The Unix timestamp (in seconds) of when the chat completion was created model: type: string description: The model used for the chat completion choices: type: array items: $ref: '#/components/schemas/ChatCompletionChoice' usage: $ref: '#/components/schemas/CompletionUsage' system_fingerprint: type: string description: >- This fingerprint represents the backend configuration that the model runs with CreateChatCompletionStreamResponse: type: object required: - id - object - created - model - choices properties: id: type: string description: A unique identifier for the chat completion object: type: string enum: - chat.completion.chunk created: type: integer description: >- The Unix timestamp (in seconds) of when the chat completion was created model: type: string description: The model used for the chat completion choices: type: array items: $ref: '#/components/schemas/ChatCompletionStreamChoice' system_fingerprint: type: string description: >- This fingerprint represents the backend configuration that the model runs with ErrorResponse: type: object required: - error properties: error: type: object required: - message - type properties: message: type: string description: A human-readable error message type: type: string description: The type of error code: type: string description: An error code identifying the error type ChatCompletionMessage: type: object required: - role - content properties: role: type: string enum: - user - assistant - developer - tool description: The role of the messages author content: oneOf: - type: string description: The contents of the message - type: array description: An array of content parts with a defined type items: $ref: '#/components/schemas/ChatCompletionMessageContentPart' name: type: string description: An optional name for the participant tool_calls: type: array description: The tool calls generated by the model items: $ref: '#/components/schemas/ChatCompletionMessageToolCall' tool_call_id: type: string description: Tool call that this message is responding to ChatCompletionTool: type: object required: - type - function properties: type: type: string enum: - function function: $ref: '#/components/schemas/FunctionDefinition' ChatCompletionToolChoice: type: object required: - type - function properties: type: type: string enum: - function function: type: object required: - name properties: name: type: string description: The name of the function to call ChatCompletionChoice: type: object properties: index: type: integer message: $ref: '#/components/schemas/ChatCompletionResponseMessage' finish_reason: type: string enum: - stop - length - function_call - content_filter required: - index - message - finish_reason CompletionUsage: type: object properties: completion_tokens: type: integer description: Number of tokens in the generated completion prompt_tokens: type: integer description: Number of tokens in the prompt total_tokens: type: integer description: Total number of tokens used in the request required: - completion_tokens - prompt_tokens - total_tokens ChatCompletionStreamChoice: type: object required: - index - delta properties: index: type: integer description: The index of the choice in the list of choices delta: $ref: '#/components/schemas/ChatCompletionStreamChoiceDelta' finish_reason: type: string enum: - stop - length - tool_calls - content_filter - function_call description: The reason the model stopped generating tokens logprobs: $ref: '#/components/schemas/ChatCompletionLogprobs' ChatCompletionMessageContentPart: oneOf: - $ref: '#/components/schemas/ChatCompletionMessageContentPartText' - $ref: '#/components/schemas/ChatCompletionMessageContentPartImage' - $ref: '#/components/schemas/ChatCompletionMessageContentPartFile' - $ref: '#/components/schemas/ChatCompletionMessageContentPartInputAudio' discriminator: propertyName: type mapping: text: $ref: '#/components/schemas/ChatCompletionMessageContentPartText' image_url: $ref: '#/components/schemas/ChatCompletionMessageContentPartImage' file: $ref: '#/components/schemas/ChatCompletionMessageContentPartFile' input_audio: $ref: '#/components/schemas/ChatCompletionMessageContentPartInputAudio' ChatCompletionMessageToolCall: type: object required: - id - type - function properties: id: type: string description: The ID of the tool call type: type: string enum: - function function: type: object required: - name - arguments 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 FunctionDefinition: type: object required: - name 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 ChatCompletionResponseMessage: type: object properties: role: type: string enum: - assistant content: type: string function_call: $ref: '#/components/schemas/ChatCompletionMessageFunctionCall' required: - role ChatCompletionStreamChoiceDelta: type: object properties: role: type: string enum: - system - user - assistant - tool description: The role of the author of this message content: type: string description: The contents of the chunk message tool_calls: type: array items: $ref: '#/components/schemas/ChatCompletionMessageToolCallChunk' ChatCompletionLogprobs: type: object properties: content: type: array items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' ChatCompletionMessageContentPartText: type: object required: - type - text properties: type: type: string enum: - text text: type: string description: The text content ChatCompletionMessageContentPartImage: type: object required: - type - image_url properties: type: type: string enum: - image_url image_url: type: object required: - url properties: url: type: string format: uri description: Either a URL of the image or the base64 encoded image data detail: type: string enum: - auto - low - high description: Specifies the detail level of the image default: auto ChatCompletionMessageContentPartFile: type: object required: - type - file properties: type: type: string enum: - file file: type: object properties: file_data: type: string description: >- A base64-encoded data URL of the file (e.g. data:application/pdf;base64,...) file_id: type: string description: A public URL to the file description: >- Provide either file_data (base64 data URL) or file_id (public URL). Supported formats vary by model, e.g. PDF is broadly supported, while TXT/CSV/DOCX/XLSX support depends on the model. ChatCompletionMessageContentPartInputAudio: type: object required: - type - input_audio properties: type: type: string enum: - input_audio input_audio: type: object required: - data - format properties: data: type: string description: Base64-encoded audio data format: type: string enum: - wav - mp3 description: The format of the encoded audio data ChatCompletionMessageFunctionCall: type: object properties: name: type: string arguments: type: string required: - name - arguments ChatCompletionMessageToolCallChunk: type: object required: - index properties: index: type: integer description: The index of the tool call in the tool calls array id: type: string description: The ID of the tool call type: type: string enum: - function 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 ChatCompletionTokenLogprob: type: object required: - token - logprob - bytes - top_logprobs properties: token: type: string description: The token logprob: type: number description: The log probability of this token bytes: type: array items: type: integer description: >- A list of integers representing the UTF-8 bytes representation of the token top_logprobs: type: array items: $ref: '#/components/schemas/ChatCompletionTopLogprob' description: List of the most likely tokens and their log probabilities ChatCompletionTopLogprob: type: object required: - token - logprob - bytes properties: token: type: string description: The token logprob: type: number description: The log probability of this token bytes: type: array items: type: integer description: >- A list of integers representing the UTF-8 bytes representation of the token securitySchemes: bearerAuth: type: http scheme: bearer bearerFormat: JWT description: Bearer token authentication. Get your API key from the dashboard. ````