> ## Documentation Index > Fetch the complete documentation index at: https://docs.sudoapp.dev/llms.txt > Use this file to discover all available pages before exploring further. # Create Chat Completion ## OpenAPI ````yaml https://sudoapp.dev/api/openapi.json post /v1/chat/completions openapi: 3.1.0 info: title: sudo-api description: '' license: name: '' version: 0.1.0 servers: [] security: - api_key: [] - privy_token: [] tags: - name: Sudo API description: 'Sudo: The Unified AI Developer Platform' paths: /v1/chat/completions: post: tags: - Router summary: Create Chat Completion operationId: create_chat_completion requestBody: content: application/json: schema: $ref: '#/components/schemas/ChatCompletionRequest' required: true responses: '200': description: Chat completion created successfully content: application/json: schema: $ref: '#/components/schemas/ChatCompletion' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Unauthorized content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '500': description: Internal server error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '502': description: Bad gateway error content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - api_key: [] components: schemas: ChatCompletionRequest: type: object required: - messages - model properties: audio: oneOf: - type: 'null' - $ref: '#/components/schemas/AudioParameters' description: >- Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Input audio is automatically detected. frequency_penalty: type: - number - 'null' format: float description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim. logit_bias: type: - object - 'null' description: >- Modify the likelihood of specified tokens appearing in the completion. Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. additionalProperties: type: integer format: int32 propertyNames: type: string logprobs: type: - boolean - 'null' description: >- Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the content of message. max_completion_tokens: type: - integer - 'null' format: int32 description: >- The maximum number of tokens that can be generated in the chat completion. The total length of input tokens and generated tokens is limited by the model's context length. minimum: 0 messages: type: array items: $ref: '#/components/schemas/ChatMessage' description: A list of messages comprising the conversation so far. metadata: type: - object - 'null' description: >- Developer-defined tags and values used for filtering completions in the dashboard. additionalProperties: type: string propertyNames: type: string modalities: type: - array - 'null' items: type: string description: >- Output types that you would like the model to generate for this request. Most models are capable of generating text, which is the default. The gpt-4o-audio-preview model can also be used to generate audio. model: type: string description: ID of the model to use. 'n': type: - integer - 'null' format: int32 description: >- How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep n as 1 to minimize costs. minimum: 0 parallel_tool_calls: type: - boolean - 'null' description: Whether to enable parallel function calling during tool use. prediction: oneOf: - type: 'null' - $ref: '#/components/schemas/PredictionContent' description: >- Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. presence_penalty: type: - number - 'null' format: float description: >- Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics. prompt_cache_key: type: - string - 'null' description: >- Developer-supplied key for grouping related requests, used to mitigate model latency and performance issues for high-traffic applications. This key will be used on best effort basis to route requests to models that have seen the same prompt_cache_key values recently. reasoning_effort: type: - string - 'null' description: >- Constrains effort on reasoning for reasoning models. Currently supported values are low, medium, and high. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. response_format: description: >- An object specifying the format that the model must output. Compatible with GPT-4 Turbo and all GPT-3.5 Turbo models newer than gpt-3.5-turbo-1106. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. seed: type: - integer - 'null' format: int64 description: >- This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. service_tier: type: - string - 'null' description: >- Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service. If set to 'auto', the system will utilize scale tier credits until they are exhausted. If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarantee. stop: type: - array - 'null' items: type: string description: Up to 4 sequences where the API will stop generating further tokens. store: type: - boolean - 'null' description: >- Whether or not to store the output of this chat completion request for use in our model distillation or evals products. stream: type: - boolean - 'null' description: >- If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. stream_options: oneOf: - type: 'null' - $ref: '#/components/schemas/StreamOptions' description: >- Options for streaming response. Only set this when you set stream: true. temperature: type: - number - 'null' format: float description: >- What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. tool_choice: description: >- Controls which (if any) tool is called by the model. 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. required means the model must call one or more tools. Specifying a particular tool via {"type": "function", "function": {"name": "my_function"}} forces the model to call that tool. tools: type: - array - 'null' items: $ref: '#/components/schemas/Tool' description: >- A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for. top_logprobs: type: - integer - 'null' format: int32 description: >- An integer between 0 and 20 specifying the number of most likely tokens to return at each token position, each with an associated log probability. logprobs must be set to true if this parameter is used. minimum: 0 top_p: type: - number - 'null' format: float description: >- An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. user: type: - string - 'null' description: >- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. ChatCompletion: type: object description: >- Represents a chat completion response returned by model, based on the provided input. required: - choices - created - id - model - object - usage properties: choices: type: array items: $ref: '#/components/schemas/Choice' description: >- A list of chat completion choices. Can be more than one if `n` is greater than 1. created: type: integer format: int64 description: >- The Unix timestamp (in seconds) of when the chat completion was created. minimum: 0 id: type: string description: A unique identifier for the chat completion. model: type: string description: The model used for the chat completion. object: type: string description: The object type, which is always `chat.completion`. service_tier: type: - string - 'null' description: >- The service tier used for processing the request. This field is only included if the `service_tier` parameter is specified in the request. system_fingerprint: type: - string - 'null' description: >- This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. usage: $ref: '#/components/schemas/Usage' description: Usage statistics for the completion request. ErrorResponse: type: object required: - error properties: error: $ref: '#/components/schemas/ErrorDetail' AudioParameters: type: object description: >- Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. required: - voice - format properties: format: type: string description: >- Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16. voice: type: string description: >- The voice the model should use to respond. Supported voices are alloy, ash, ballad, coral, echo fable, onyx, nova, sage, shimmer, and verse. ChatMessage: oneOf: - type: object required: - content - role properties: content: $ref: '#/components/schemas/MessageContent' description: The contents of the developer message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. role: type: string enum: - developer - type: object required: - content - role properties: content: $ref: '#/components/schemas/MessageContent' description: The contents of the system message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. role: type: string enum: - system - type: object required: - content - role properties: content: $ref: '#/components/schemas/MessageContent' description: The contents of the user message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. role: type: string enum: - user - type: object required: - content - role properties: audio: oneOf: - type: 'null' - $ref: '#/components/schemas/AssistantAudioId' description: An object that references an audio output from the model. content: $ref: '#/components/schemas/MessageContent' description: The contents of the assistant message. name: type: - string - 'null' description: >- An optional name for the participant. Provides the model information to differentiate between participants of the same role. refusal: type: - string - 'null' description: The refusal message generated by the model. role: type: string enum: - assistant tool_calls: type: - array - 'null' items: $ref: '#/components/schemas/ToolCall' description: The tool calls generated by the model, such as function calls. - type: object required: - content - tool_call_id - role properties: content: $ref: '#/components/schemas/MessageContent' description: The contents of the tool message. role: type: string enum: - tool tool_call_id: type: string description: Tool call that this message is responding to. description: A message in a chat completion request or response. PredictionContent: type: object description: >- Configuration for a Predicted Output, which can greatly improve response times when large parts of the model response are known ahead of time. required: - type - content properties: content: type: string description: >- The content that should be used as the basis for the prediction. This should be the exact content of a previous response from the model, including all formatting, which you would like the model to use as a template for the current response. type: type: string description: The prediction type. Currently only "content" is supported. StreamOptions: type: object description: 'Options for streaming response. Only set this when you set stream: true.' properties: include_usage: type: - boolean - 'null' description: >- If set, an additional chunk will be streamed before the data: [DONE] message. The usage field on this chunk shows the token usage statistics for the entire request, and the choices field will always be an empty array. All other chunks will also include a usage field, but with a null value. Tool: type: object description: A tool the model may call. required: - function - type properties: function: $ref: '#/components/schemas/Function' description: The function definition. type: type: string description: The type of the tool. Currently, only `function` is supported. Choice: type: object description: A chat completion choice. required: - finish_reason - index - message properties: finish_reason: type: string description: >- The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, or `tool_calls` if the model called a tool. index: type: integer format: int32 description: The index of the choice in the list of choices. minimum: 0 logprobs: description: Log probability information for the choice. message: $ref: '#/components/schemas/MessageResponse' description: A chat completion message generated by the model. Usage: type: object description: Usage statistics for the completion request. required: - completion_tokens - prompt_tokens - total_tokens properties: completion_tokens: type: integer format: int32 description: Number of tokens in the generated completion. minimum: 0 completion_tokens_details: description: >- Breakdown of tokens used in a completion. Not supported, we will always set to Null prompt_tokens: type: integer format: int32 description: Number of tokens in the prompt. minimum: 0 prompt_tokens_details: description: >- Breakdown of tokens used in the prompt. Not supported, we will always set to Null total_tokens: type: integer format: int32 description: Total number of tokens used in the request (prompt + completion). minimum: 0 ErrorDetail: type: object required: - message - type properties: message: type: string type: type: string MessageContent: oneOf: - type: string description: Plain text content - type: array items: $ref: '#/components/schemas/ContentPart' description: Array of structured content parts supporting multimodal inputs description: >- Message content, which can be either plain text or an array of structured content parts (text, images, files, audio) AssistantAudioId: type: object description: References an audio output from the assistant. required: - id properties: id: type: string description: Unique identifier for the audio output. ToolCall: type: object description: A tool call generated by the model. required: - id - type - function properties: function: $ref: '#/components/schemas/ToolCallFunction' description: The function that the model called. id: type: string description: The ID of the tool call. type: type: string description: The type of the tool. Currently, only `function` is supported. Function: type: object description: The definition of a function that can be called by the model. required: - name properties: description: type: - string - 'null' description: >- A description of what the function does, used by the model to choose when and how to call the function. name: type: string description: >- The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: description: >- The parameters the functions accepts, described as a JSON Schema object. See the guide for examples, and the JSON Schema reference for documentation about the format. Omitting parameters defines a function with an empty parameter list. strict: type: - boolean - 'null' description: >- Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the parameters field. Only a subset of JSON Schema is supported when strict is true. MessageResponse: type: object description: A chat completion message generated by the model. required: - role properties: annotations: description: A list of annotations for the message content. audio: description: >- If the audio output modality is requested, this object contains data about the audio response from the model. content: type: - string - 'null' description: The contents of the message. refusal: type: - string - 'null' description: The refusal message generated by the model. role: type: string description: The role of the author of this message. tool_calls: type: - array - 'null' items: $ref: '#/components/schemas/ToolCall' description: The tool calls generated by the model, such as function calls. ContentPart: oneOf: - type: object description: Text content part required: - text - type properties: text: type: string description: The text content type: type: string enum: - input_text - type: object description: Image content part required: - detail - type properties: detail: type: string description: Level of detail for image processing ("low", "high", "auto") file_id: type: - string - 'null' description: ID of a previously uploaded file containing the image image_url: type: - string - 'null' description: URL of the image to process type: type: string enum: - input_image - type: object description: File content part for document processing required: - type properties: file_data: type: - string - 'null' description: Base64-encoded file data file_id: type: - string - 'null' description: ID of a previously uploaded file file_url: type: - string - 'null' description: URL of the file to process filename: type: - string - 'null' description: Name of the file type: type: string enum: - input_file - type: object description: Audio content part required: - input_audio - type properties: input_audio: $ref: '#/components/schemas/Audio' description: Audio input data and format type: type: string enum: - input_audio description: >- A part of message content, supporting different content types (text, images, files, audio) for multimodal input ToolCallFunction: type: object description: The function that was called by the model. required: - name - arguments properties: arguments: type: string description: >- The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. Audio: type: object description: Audio input data required: - data - format properties: data: type: string description: Base64-encoded audio data format: type: string description: Audio format (e.g., "wav", "mp3") ````