> ## Documentation Index > Fetch the complete documentation index at: https://io-migration.mintlify.site/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/create-chat-completion.json post /api/v1/chat/completions openapi: 3.1.0 info: title: IO Intelligence version: '1.0' servers: - url: https://api.intelligence.io.solutions security: - sec0: [] paths: /api/v1/chat/completions: post: summary: Create Chat Completion description: Creates a model response for the given chat conversation. operationId: create-chat-completion requestBody: content: application/json: schema: type: object required: - model - messages properties: model: type: string description: >- ID of the model to use. See the model endpoint compatibility table for details on which models work with the Chat API. messages: type: array description: The conversation history reasoning_content: type: boolean description: Enable reasoning content in response default: false frequency_penalty: type: integer 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. default: 0 format: int32 logit_bias: type: object 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. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. properties: {} logprobs: type: boolean 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. 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, each with an associated log probability. logprobs must be set to true if this parameter is used. format: int32 max_tokens: type: integer description: >- Deprecated. The maximum number of tokens that can be generated in the chat completion. This value can be used to control costs for text generated via API. This value is now deprecated in favor of max_completion_tokens, and is not compatible with o1 series models. format: int32 max_completion_tokens: type: integer description: >- An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. format: int32 'n': type: integer 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. default: 1 format: int32 presence_penalty: type: integer 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. default: 0 format: int32 response_format: type: object description: >- An object specifying the format that the model must output. Setting to { "type": "json_schema", "json_schema": {...} } enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide. Setting to { "type": "json_object" } enables JSON mode, which ensures the message the model generates is valid JSON. Important: when using JSON mode, you must also instruct the model to produce JSON yourself via a system or user message. Without this, the model may generate an unending stream of whitespace until the generation reaches the token limit, resulting in a long-running and seemingly "stuck" request. Also note that the message content may be partially cut off if finish_reason="length", which indicates the generation exceeded max_tokens or the conversation exceeded the max context length. properties: {} seed: type: integer 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, and you should refer to the system_fingerprint response parameter to monitor changes in the backend. format: int32 stop: type: array description: >- Up to 4 sequences where the API will stop generating further tokens. items: type: string stream: type: boolean description: >- If set, partial message deltas will be sent, like in ChatGPT. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message. Example Python code. default: false stream_options: type: object description: >- Options for streaming response. Only set this when you set stream: true. properties: {} temperature: type: integer 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. We generally recommend altering this or top_p but not both. default: 0.7 format: int32 top_p: type: integer 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. We generally recommend altering this or temperature but not both. default: 1 format: int32 tools: type: array 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. A max of 128 functions are supported. tool_choice: type: string 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. none is the default when no tools are present. auto is the default if tools are present. default: '"none"' parallel_tool_calls: type: boolean description: Whether to enable parallel function calling during tool use. default: false user: type: string description: >- A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. best_of: type: integer format: int32 use_beam_search: type: boolean default: false top_k: type: integer default: -1 format: int32 min_p: type: integer default: 0 format: int32 repetition_penalty: type: integer default: 1 format: int32 length_penalty: type: integer default: 1 format: int32 stop_token_ids: type: array items: type: integer format: int32 include_stop_str_in_output: type: boolean default: false ignore_eos: type: boolean default: false min_tokens: type: integer default: 0 format: int32 skip_special_tokens: type: boolean default: true spaces_between_special_tokens: type: boolean default: true truncate_prompt_tokens: type: integer format: int32 prompt_logprobs: type: integer format: int32 echo: type: boolean description: >- If true, the new message will be prepended with the last message if they belong to the same role. default: false add_generation_prompt: type: boolean description: >- If true, the generation prompt will be added to the chat template. This is a parameter used by chat template in tokenizer config of the model. default: true continue_final_message: type: boolean description: >- If this is set, the chat will be formatted so that the final message in the chat is open-ended, without any EOS tokens. The model will continue this message rather than starting a new one. This allows you to "prefill" part of the model's response for it. Cannot be used at the same time as add_generation_prompt. default: false add_special_tokens: type: boolean description: >- If true, special tokens (e.g. BOS) will be added to the prompt on top of what is added by the chat template. For most models, the chat template takes care of adding the special tokens so this should be set to false (as is the default). default: false documents: type: array description: >- A list of dicts representing documents that will be accessible to the model if it is performing RAG (retrieval-augmented generation). If the template does not support RAG, this argument will have no effect. We recommend that each document should be a dict containing "title" and "text" keys. chat_template: type: string description: >- A Jinja template to use for this conversion. As of transformers v4.44, default chat template is no longer allowed, so you must provide a chat template if the tokenizer does not define one. chat_template_kwargs: type: object description: >- Additional kwargs to pass to the template renderer. Will be accessible by the chat template. properties: {} guided_json: type: string description: If specified, the output will follow the JSON schema. guided_regex: type: string description: If specified, the output will follow the regex pattern. guided_choice: type: array description: If specified, the output will be exactly one of the choices. items: type: string guided_grammar: type: string description: >- If specified, the output will follow the context free grammar. guided_decoding_backend: type: string description: >- If specified, will override the default guided decoding backend of the server for this specific request. If set, must be either 'outlines' / 'lm-format-enforcer' guided_whitespace_pattern: type: string description: >- If specified, will override the default whitespace pattern for guided json decoding. priority: type: integer description: >- The priority of the request (lower means earlier handling; default: 0). Any priority other than 0 will raise an error if the served model does not use priority scheduling. default: 0 format: int32 request_id: type: string description: >- The request_id related to this request. If the caller does not set it, a random_uuid will be generated. This id is used through out the inference process and return in response. responses: '200': description: '200' content: application/json: examples: Result: value: id: 0194e036-5a18-26ac-99d8-be455a6262b object: chat.completion created: 1738928445 model: CohereForAI/c4ai-command-r-plus-08-2024 choices: - index: 0 message: role: assistant reasoning_content: null content: Hi. How can I help? tool_calls: [] logprobs: null finish_reason: stop stop_reason: null usage: prompt_tokens: 17 total_tokens: 25 completion_tokens: 8 prompt_tokens_details: null prompt_logprobs: null schema: type: object properties: id: type: string example: 0194e036-5a18-26ac-99d8-be455a6262b object: type: string example: chat.completion created: type: integer example: 1738928445 default: 0 model: type: string example: CohereForAI/c4ai-command-r-plus-08-2024 choices: type: array items: type: object properties: index: type: integer example: 0 default: 0 message: type: object properties: role: type: string example: assistant reasoning_content: {} content: type: string example: Hi. How can I help? tool_calls: type: array logprobs: {} finish_reason: type: string example: stop stop_reason: {} usage: type: object properties: prompt_tokens: type: integer example: 17 default: 0 total_tokens: type: integer example: 25 default: 0 completion_tokens: type: integer example: 8 default: 0 prompt_tokens_details: {} prompt_logprobs: {} '404': description: '404' content: application/json: examples: Result: value: string schema: type: string example: string '422': description: '422' content: application/json: examples: Validation Error: value: detail: - loc: - string - 0 msg: string type: string schema: type: object properties: detail: type: array items: type: object properties: loc: type: array msg: type: string example: string type: type: string example: string deprecated: false security: [] components: securitySchemes: sec0: type: oauth2 flows: {} ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.