**Starting a new project?** We recommend trying [Responses](/docs/api-reference/responses) to take advantage of the latest OpenAI platform features. Compare [Chat Completions with Responses](/docs/guides/responses-vs-chat-completions?api-mode=responses). --- Creates a model response for the given chat conversation. Learn more in the [text generation](/docs/guides/text-generation), [vision](/docs/guides/vision), and [audio](/docs/guides/audio) guides. Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, [refer to the reasoning guide](/docs/guides/reasoning).

Starting a new project? We recommend trying [Responses](/docs/api-reference/responses) to take advantage of the latest OpenAI platform features. Compare [Chat Completions with Responses](/docs/guides/responses-vs-chat-completions?api-mode=responses). --- Creates a model response for the given chat conversation. Learn more in the [text generation](/docs/guides/text-generation), [vision](/docs/guides/vision), and [audio](/docs/guides/audio) guides. Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, [refer to the reasoning guide](/docs/guides/reasoning).

POST /chat/completions

Api key auth

application/json

Body Required

metadata object | null

Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard.

Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters.
Hide metadata attribute Show metadata attribute object | null
- * string Additional properties
temperature number | null

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.

Minimum value is 0, maximum value is 2. Default value is 1.
top_p number | null

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.

Minimum value is 0, maximum value is 1. Default value is 1.
user string

A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
messages array[object] Required

A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio.

At least 1 element.
One of:
ChatCompletionRequestDeveloperMessage object ChatCompletionRequestSystemMessage object ChatCompletionRequestUserMessage object ChatCompletionRequestAssistantMessage object ChatCompletionRequestToolMessage object ChatCompletionRequestFunctionMessage object Deprecated
Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, developer messages replace the previous system messages.
Hide attributes Show attributes

content string | array[object] Required

The contents of the developer message.

One of:
Text content string Array of content parts array[object]

The contents of the developer message.

An array of content parts with a defined type. For developer messages, only type text is supported.

Learn about text inputs.

At least 1 element.

Hide attributes Show attributes object

type string Required

The type of the content part.

Value is text.

text string Required

The text content.

role string Required

The role of the messages author, in this case developer.

Value is developer.

name string

An optional name for the participant. Provides the model information to differentiate between participants of the same role.
Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, use developer messages for this purpose instead.
Hide attributes Show attributes

content string | array[object] Required

The contents of the system message.

One of:
Text content string Array of content parts array[object]

The contents of the system message.

An array of content parts with a defined type. For system messages, only type text is supported.

At least 1 element.

Hide attributes Show attributes object

type string Required

The type of the content part.

Value is text.

text string Required

The text content.

role string Required

The role of the messages author, in this case system.

Value is system.

name string

An optional name for the participant. Provides the model information to differentiate between participants of the same role.
Messages sent by an end user, containing prompts or additional context information.
Hide attributes Show attributes

content string | array[object] Required

The contents of the user message.

One of:
Text content string Array of content parts array[object]

The text contents of the message.

An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text, image, or audio inputs.

At least 1 element.

One of:
ChatCompletionRequestMessageContentPartText object ChatCompletionRequestMessageContentPartImage object ChatCompletionRequestMessageContentPartAudio object ChatCompletionRequestMessageContentPartFile object

Learn about image inputs.

Hide attributes Show attributes

type string Required

The type of the content part.

Value is image_url.

image_url object Required

Hide image_url attributes Show image_url attributes object

url string(uri) Required

Either a URL of the image or the base64 encoded image data.

detail string

Specifies the detail level of the image. Learn more in the Vision guide.

Values are auto, low, or high. Default value is auto.

Learn about audio inputs.

Hide attributes Show attributes

type string Required

The type of the content part. Always input_audio.

Value is input_audio.

input_audio object Required

Hide input_audio attributes Show input_audio attributes object

data string Required

Base64 encoded audio data.

format string Required

The format of the encoded audio data. Currently supports "wav" and "mp3".

Values are wav or mp3.

Learn about file inputs for text generation.

Hide attributes Show attributes

type string Required

The type of the content part. Always file.

Value is file.

file object Required

Hide file attributes Show file attributes object

filename string

The name of the file, used when passing the file to the model as a string.

file_data string

The base64 encoded file data, used when passing the file to the model as a string.

file_id string

The ID of an uploaded file to use as input.

role string Required

The role of the messages author, in this case user.

Value is user.

name string

An optional name for the participant. Provides the model information to differentiate between participants of the same role.
Messages sent by the model in response to user messages.
Hide attributes Show attributes

content string | null | array[object]

The contents of the assistant message. Required unless tool_calls or function_call is specified.

One of:
Text content string | null Array of content parts array[object] | null

The contents of the assistant message.

An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal.

At least 1 element.

One of:
ChatCompletionRequestMessageContentPartText object ChatCompletionRequestMessageContentPartRefusal object

refusal string | null

The refusal message by the assistant.

role string Required

The role of the messages author, in this case assistant.

Value is assistant.

name string

An optional name for the participant. Provides the model information to differentiate between participants of the same role.

audio object | null

Data about a previous audio response from the model. Learn more.

Hide audio attribute Show audio attribute object | null

id string Required

Unique identifier for a previous audio response from the model.

tool_calls array[object]

The tool calls generated by the model, such as function calls.

Hide tool_calls attributes Show tool_calls attributes object

id string Required

The ID of the tool call.

type string Required

The type of the tool. Currently, only function is supported.

Value is function.

function object Required

The function that the model called.

Hide function attributes Show function attributes object

name string Required

The name of the function to call.

arguments string Required

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.

function_call object | null Deprecated

Deprecated and replaced by tool_calls. The name and arguments of a function that should be called, as generated by the model.

Hide function_call attributes Show function_call attributes object | null Deprecated

arguments string Required

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 string Required

The name of the function to call.
Hide attributes Show attributes

role string Required

The role of the messages author, in this case tool.

Value is tool.

content string | array[object] Required

The contents of the tool message.

One of:
Text content string Array of content parts array[object]

The contents of the tool message.

An array of content parts with a defined type. For tool messages, only type text is supported.

At least 1 element.

Hide attributes Show attributes object

type string Required

The type of the content part.

Value is text.

text string Required

The text content.

tool_call_id string Required

Tool call that this message is responding to.
Hide attributes Show attributes

role string Required

The role of the messages author, in this case function.

Value is function.

content string | null Required

The contents of the function message.

name string Required

The name of the function to call.
model string Required

Model ID used to generate the response, like gpt-4o or o1. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the model guide to browse and compare available models.

Any of:
string-1 string string-2 string

Values are o3-mini, o3-mini-2025-01-31, o1, o1-2024-12-17, o1-preview, o1-preview-2024-09-12, o1-mini, o1-mini-2024-09-12, gpt-4o, gpt-4o-2024-11-20, gpt-4o-2024-08-06, gpt-4o-2024-05-13, gpt-4o-audio-preview, gpt-4o-audio-preview-2024-10-01, gpt-4o-audio-preview-2024-12-17, gpt-4o-mini-audio-preview, gpt-4o-mini-audio-preview-2024-12-17, gpt-4o-search-preview, gpt-4o-mini-search-preview, gpt-4o-search-preview-2025-03-11, gpt-4o-mini-search-preview-2025-03-11, chatgpt-4o-latest, gpt-4o-mini, gpt-4o-mini-2024-07-18, gpt-4-turbo, gpt-4-turbo-2024-04-09, gpt-4-0125-preview, gpt-4-turbo-preview, gpt-4-1106-preview, gpt-4-vision-preview, gpt-4, gpt-4-0314, gpt-4-0613, gpt-4-32k, gpt-4-32k-0314, gpt-4-32k-0613, gpt-3.5-turbo, gpt-3.5-turbo-16k, gpt-3.5-turbo-0301, gpt-3.5-turbo-0613, gpt-3.5-turbo-1106, gpt-3.5-turbo-0125, or gpt-3.5-turbo-16k-0613.
modalities array[string] | null

Output types that you would like the model to generate. Most models are capable of generating text, which is the default:

["text"]

The gpt-4o-audio-preview model can also be used to generate audio. To request that this model generate both text and audio responses, you can use:

["text", "audio"]

Values are text or audio.
reasoning_effort string | null

o-series models only

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.

Values are low, medium, or high. Default value is medium.
max_completion_tokens integer | null

An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
frequency_penalty number | null

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.

Minimum value is -2, maximum value is 2. Default value is 0.
presence_penalty number | null

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.

Minimum value is -2, maximum value is 2. Default value is 0.
web_search_options object

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
Hide web_search_options attributes Show web_search_options attributes object
- user_location object | null
  
  Approximate location parameters for the search.
  Hide user_location attributes Show user_location attributes object | null
  
  type string Required
  
  The type of location approximation. Always approximate.
  
  Value is approximate.
  
  approximate object Required
  
  Approximate location parameters for the search.
  
  Hide approximate attributes Show approximate attributes object
  
  country string
  
  The two-letter ISO country code of the user, e.g. US.
  
  region string
  
  Free text input for the region of the user, e.g. California.
  
  city string
  
  Free text input for the city of the user, e.g. San Francisco.
  
  timezone string
  
  The IANA timezone of the user, e.g. America/Los_Angeles.
- search_context_size string
  
  High level guidance for the amount of context window space to use for the search. One of low, medium, or high. medium is the default.
  
  Values are low, medium, or high. Default value is medium.
top_logprobs integer | null

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 value is 0, maximum value is 20.
response_format object

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 the older JSON mode, which ensures the message the model generates is valid JSON. Using json_schema is preferred for models that support it.
One of:
ResponseFormatText object ResponseFormatJsonSchema object ResponseFormatJsonObject object
Default response format. Used to generate text responses.
Hide attribute Show attribute

type string Required

The type of response format being defined. Always text.

Value is text.
JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
Hide attributes Show attributes

type string Required

The type of response format being defined. Always json_schema.

Value is json_schema.

json_schema object Required

Structured Outputs configuration options, including a JSON Schema.

Hide json_schema attributes Show json_schema attributes object

description string

A description of what the response format is for, used by the model to determine how to respond in the format.

name string Required

The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64.

schema object

The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas here.

Additional properties are allowed.

strict boolean | null

Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the schema field. Only a subset of JSON Schema is supported when strict is true. To learn more, read the Structured Outputs guide.

Default value is false.
JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so.
Hide attribute Show attribute

type string Required

The type of response format being defined. Always json_object.

Value is json_object.
service_tier string | null
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', and the Project is Scale tier enabled, the system will utilize scale tier credits until they are exhausted.
- If set to 'auto', and the Project is not Scale tier enabled, the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
- If set to 'default', the request will be processed using the default service tier with a lower uptime SLA and no latency guarentee.
- When not set, the default behavior is 'auto'.
When this parameter is set, the response body will include the service_tier utilized.
Values are auto or default. Default value is auto.
audio object | null

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.
Hide audio attributes Show audio attributes object | null
- voice string Required
  
  The voice to use when generating the audio. Supported voices are alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, and verse. Previews of the voices are available in the Text to speech guide.
  
  Any of:
  string-1 string string-2 string
  
  Values are alloy, ash, ballad, coral, echo, fable, onyx, nova, sage, shimmer, or verse.
- format string Required
  
  Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16.
  
  Values are wav, mp3, flac, opus, or pcm16.
store boolean | null

Whether or not to store the output of this chat completion request for use in our model distillation or evals products.

Default value is false.
stream boolean | null

If set to true, the model response data will be streamed to the client as it is generated using server-sent events. See the Streaming section below for more information, along with the streaming responses guide for more information on how to handle the streaming events.

Default value is false.
stop string | null | array[string]

Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.

One of:
string-1 string | null array-2 array[string] | null

Default value is <|endoftext|>.

At least 1 but not more than 4 elements.
logit_bias object | null

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.
Hide logit_bias attribute Show logit_bias attribute object | null
- * integer Additional properties
logprobs boolean | null

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 value is false.
max_tokens integer | null 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.
n integer | null

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 value is 1, maximum value is 128. Default value is 1.
prediction object | null

Static predicted output content, such as the content of a text file that is being regenerated.
Hide prediction attributes Show prediction attributes object | null
- type string Required
  
  The type of the predicted content you want to provide. This type is currently always content.
  
  Value is content.
- content string | array[object] Required
  
  The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly.
  
  One of:
  Text content string Array of content parts array[object]
  
  The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes.
  
  An array of content parts with a defined type. Supported options differ based on the model being used to generate the response. Can contain text inputs.
  
  Learn about text inputs.
  
  At least 1 element.
  
  Hide attributes Show attributes object
  
  type string Required
  
  The type of the content part.
  
  Value is text.
  
  text string Required
  
  The text content.
seed integer(int64) | null

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.
stream_options object | null

Options for streaming response. Only set this when you set stream: true.
Hide stream_options attribute Show stream_options attribute object | null
- include_usage boolean
  
  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. NOTE: If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request.
tools array[object]

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.
Hide tools attributes Show tools attributes object
- type string Required
  
  The type of the tool. Currently, only function is supported.
  
  Value is function.
- function object Required
  Hide function attributes Show function attributes object
  
  description string
  
  A description of what the function does, used by the model to choose when and how to call the function.
  
  name string Required
  
  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 object
  
  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.
  
  Additional properties are allowed.
  
  strict boolean | null
  
  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. Learn more about Structured Outputs in the function calling guide.
  
  Default value is false.
tool_choice string | object

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.
One of:
string-1 string ChatCompletionNamedToolChoice object

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.

Values are none, auto, or required.
Specifies a tool the model should use. Use to force the model to call a specific function.
Hide attributes Show attributes

type string Required

The type of the tool. Currently, only function is supported.

Value is function.

function object Required

Hide function attribute Show function attribute object

name string Required

The name of the function to call.
parallel_tool_calls boolean

Whether to enable parallel function calling during tool use.

Default value is true.
function_call string | object Deprecated

Deprecated in favor of tool_choice.

Controls which (if any) function is called by the model.

none means the model will not call a function and instead generates a message.

auto means the model can pick between generating a message or calling a function.

Specifying a particular function via {"name": "my_function"} forces the model to call that function.

none is the default when no functions are present. auto is the default if functions are present.
One of:
string-1 string ChatCompletionFunctionCallOption object

none means the model will not call a function and instead generates a message. auto means the model can pick between generating a message or calling a function.

Values are none or auto.
Specifying a particular function via {"name": "my_function"} forces the model to call that function.
Hide attribute Show attribute

name string Required

The name of the function to call.
functions array[object] Deprecated

Deprecated in favor of tools.

A list of functions the model may generate JSON inputs for.

At least 1 but not more than 128 elements.
Hide functions attributes Show functions attributes object Deprecated
- description string
  
  A description of what the function does, used by the model to choose when and how to call the function.
- name string Required
  
  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 object
  
  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.
  
  Additional properties are allowed.

Responses

200

application/json

application/json text/event-stream

OK
Hide response attributes Show response attributes object
- id string Required
  
  A unique identifier for the chat completion.
- choices array[object] Required
  
  A list of chat completion choices. Can be more than one if n is greater than 1.
  
  Hide choices attributes Show choices attributes object
  
  finish_reason string Required
  
  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, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.
  
  Values are stop, length, tool_calls, content_filter, or function_call.
  
  index integer Required
  
  The index of the choice in the list of choices.
  
  message object Required
  
  A chat completion message generated by the model.
  
  Hide message attributes Show message attributes object
  
  content string | null Required
  
  The contents of the message.
  
  refusal string | null Required
  
  The refusal message generated by the model.
  
  tool_calls array[object]
  
  The tool calls generated by the model, such as function calls.
  
  Hide tool_calls attributes Show tool_calls attributes object
  
  id string Required
  
  The ID of the tool call.
  
  type string Required
  
  The type of the tool. Currently, only function is supported.
  
  Value is function.
  
  function object Required
  
  The function that the model called.
  
  Hide function attributes Show function attributes object
  
  name string Required
  
  The name of the function to call.
  
  arguments string Required
  
  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.
  
  annotations array[object]
  
  Annotations for the message, when applicable, as when using the web search tool.
  
  A URL citation when using web search.
  
  Hide annotations attributes Show annotations attributes object
  
  type string Required
  
  The type of the URL citation. Always url_citation.
  
  Value is url_citation.
  
  url_citation object Required
  
  A URL citation when using web search.
  
  Hide url_citation attributes Show url_citation attributes object
  
  end_index integer Required
  
  The index of the last character of the URL citation in the message.
  
  start_index integer Required
  
  The index of the first character of the URL citation in the message.
  
  url string Required
  
  The URL of the web resource.
  
  title string Required
  
  The title of the web resource.
  
  role string Required
  
  The role of the author of this message.
  
  Value is assistant.
  
  function_call object Deprecated
  
  Deprecated and replaced by tool_calls. The name and arguments of a function that should be called, as generated by the model.
  
  Hide function_call attributes Show function_call attributes object Deprecated
  
  arguments string Required
  
  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 string Required
  
  The name of the function to call.
  
  audio object | null
  
  If the audio output modality is requested, this object contains data about the audio response from the model. Learn more.
  
  Hide audio attributes Show audio attributes object | null
  
  id string Required
  
  Unique identifier for this audio response.
  
  expires_at integer Required
  
  The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations.
  
  data string Required
  
  Base64 encoded audio bytes generated by the model, in the format specified in the request.
  
  transcript string Required
  
  Transcript of the audio generated by the model.
  
  logprobs object | null Required
  
  Log probability information for the choice.
  
  Hide logprobs attributes Show logprobs attributes object | null
  
  content array[object] | null Required
  
  A list of message content tokens with log probability information.
  
  Hide content attributes Show content attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
  
  top_logprobs array[object] Required
  
  List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.
  
  Hide top_logprobs attributes Show top_logprobs attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
  
  refusal array[object] | null Required
  
  A list of message refusal tokens with log probability information.
  
  Hide refusal attributes Show refusal attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
  
  top_logprobs array[object] Required
  
  List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.
  
  Hide top_logprobs attributes Show top_logprobs attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
- created integer Required
  
  The Unix timestamp (in seconds) of when the chat completion was created.
- model string Required
  
  The model used for the chat completion.
- service_tier string | null
  
  The service tier used for processing the request.
  
  Values are scale or default.
- system_fingerprint string
  
  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.
- object string Required
  
  The object type, which is always chat.completion.
  
  Value is chat.completion.
- usage object
  
  Usage statistics for the completion request.
  
  Hide usage attributes Show usage attributes object
  
  completion_tokens integer Required
  
  Number of tokens in the generated completion.
  
  Default value is 0.
  
  prompt_tokens integer Required
  
  Number of tokens in the prompt.
  
  Default value is 0.
  
  total_tokens integer Required
  
  Total number of tokens used in the request (prompt + completion).
  
  Default value is 0.
  
  completion_tokens_details object
  
  Breakdown of tokens used in a completion.
  
  Hide completion_tokens_details attributes Show completion_tokens_details attributes object
  
  accepted_prediction_tokens integer
  
  When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
  
  Default value is 0.
  
  audio_tokens integer
  
  Audio input tokens generated by the model.
  
  Default value is 0.
  
  reasoning_tokens integer
  
  Tokens generated by the model for reasoning.
  
  Default value is 0.
  
  rejected_prediction_tokens integer
  
  When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits.
  
  Default value is 0.
  
  prompt_tokens_details object
  
  Breakdown of tokens used in the prompt.
  
  Hide prompt_tokens_details attributes Show prompt_tokens_details attributes object
  
  audio_tokens integer
  
  Audio input tokens present in the prompt.
  
  Default value is 0.
  
  cached_tokens integer
  
  Cached tokens present in the prompt.
  
  Default value is 0.
Hide response attributes Show response attributes object
- id string Required
  
  A unique identifier for the chat completion. Each chunk has the same ID.
- choices array[object] Required
  
  A list of chat completion choices. Can contain more than one elements if n is greater than 1. Can also be empty for the last chunk if you set stream_options: {"include_usage": true}.
  
  Hide choices attributes Show choices attributes object
  
  delta object Required
  
  A chat completion delta generated by streamed model responses.
  
  Hide delta attributes Show delta attributes object
  
  content string | null
  
  The contents of the chunk message.
  
  function_call object Deprecated
  
  Deprecated and replaced by tool_calls. The name and arguments of a function that should be called, as generated by the model.
  
  Hide function_call attributes Show function_call attributes object Deprecated
  
  arguments string
  
  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 string
  
  The name of the function to call.
  
  tool_calls array[object]
  
  Hide tool_calls attributes Show tool_calls attributes object
  
  index integer Required
  
  id string
  
  The ID of the tool call.
  
  type string
  
  The type of the tool. Currently, only function is supported.
  
  Value is function.
  
  function object
  
  Hide function attributes Show function attributes object
  
  name string
  
  The name of the function to call.
  
  arguments string
  
  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.
  
  role string
  
  The role of the author of this message.
  
  Values are developer, system, user, assistant, or tool.
  
  refusal string | null
  
  The refusal message generated by the model.
  
  logprobs object | null
  
  Log probability information for the choice.
  
  Hide logprobs attributes Show logprobs attributes object | null
  
  content array[object] | null Required
  
  A list of message content tokens with log probability information.
  
  Hide content attributes Show content attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
  
  top_logprobs array[object] Required
  
  List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.
  
  Hide top_logprobs attributes Show top_logprobs attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
  
  refusal array[object] | null Required
  
  A list of message refusal tokens with log probability information.
  
  Hide refusal attributes Show refusal attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
  
  top_logprobs array[object] Required
  
  List of the most likely tokens and their log probability, at this token position. In rare cases, there may be fewer than the number of requested top_logprobs returned.
  
  Hide top_logprobs attributes Show top_logprobs attributes object
  
  token string Required
  
  The token.
  
  logprob number Required
  
  The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value -9999.0 is used to signify that the token is very unlikely.
  
  bytes array[integer] | null Required
  
  A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be null if there is no bytes representation for the token.
  
  finish_reason string | null Required
  
  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, tool_calls if the model called a tool, or function_call (deprecated) if the model called a function.
  
  Values are stop, length, tool_calls, content_filter, or function_call.
  
  index integer Required
  
  The index of the choice in the list of choices.
- created integer Required
  
  The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.
- model string Required
  
  The model to generate the completion.
- service_tier string | null
  
  The service tier used for processing the request.
  
  Values are scale or default.
- system_fingerprint string
  
  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.
- object string Required
  
  The object type, which is always chat.completion.chunk.
  
  Value is chat.completion.chunk.
- usage object
  
  Usage statistics for the completion request.
  
  Hide usage attributes Show usage attributes object
  
  completion_tokens integer Required
  
  Number of tokens in the generated completion.
  
  Default value is 0.
  
  prompt_tokens integer Required
  
  Number of tokens in the prompt.
  
  Default value is 0.
  
  total_tokens integer Required
  
  Total number of tokens used in the request (prompt + completion).
  
  Default value is 0.
  
  completion_tokens_details object
  
  Breakdown of tokens used in a completion.
  
  Hide completion_tokens_details attributes Show completion_tokens_details attributes object
  
  accepted_prediction_tokens integer
  
  When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.
  
  Default value is 0.
  
  audio_tokens integer
  
  Audio input tokens generated by the model.
  
  Default value is 0.
  
  reasoning_tokens integer
  
  Tokens generated by the model for reasoning.
  
  Default value is 0.
  
  rejected_prediction_tokens integer
  
  When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits.
  
  Default value is 0.
  
  prompt_tokens_details object
  
  Breakdown of tokens used in the prompt.
  
  Hide prompt_tokens_details attributes Show prompt_tokens_details attributes object
  
  audio_tokens integer
  
  Audio input tokens present in the prompt.
  
  Default value is 0.
  
  cached_tokens integer
  
  Cached tokens present in the prompt.
  
  Default value is 0.

POST /chat/completions

curl \
 --request POST 'https://api.openai.com/v1/chat/completions' \
 --header "Authorization: Bearer $ACCESS_TOKEN" \
 --header "Content-Type: application/json" \
 --data '{"metadata":{"additionalProperty1":"string","additionalProperty2":"string"},"temperature":1,"top_p":1,"user":"user-1234","messages":[{"content":"string","role":"developer","name":"string"}],"model":"gpt-4o","modalities":["text"],"reasoning_effort":"medium","max_completion_tokens":42,"frequency_penalty":0,"presence_penalty":0,"web_search_options":{"user_location":{"type":"approximate","approximate":{"country":"string","region":"string","city":"string","timezone":"string"}},"search_context_size":"medium"},"top_logprobs":42,"response_format":{"type":"text"},"service_tier":"auto","audio":{"voice":"ash","format":"wav"},"store":false,"stream":false,"stop":"\u003c|endoftext|\u003e","logit_bias":{"additionalProperty1":42,"additionalProperty2":42},"logprobs":false,"max_tokens":42,"n":1,"prediction":{"type":"content","content":"string"},"seed":42,"stream_options":{"include_usage":true},"tools":[{"type":"function","function":{"description":"string","name":"string","parameters":{},"strict":false}}],"tool_choice":"none","parallel_tool_calls":true,"function_call":"none","functions":[{"description":"string","name":"string","parameters":{}}]}'

Request examples

{
  "metadata": {
    "additionalProperty1": "string",
    "additionalProperty2": "string"
  },
  "temperature": 1,
  "top_p": 1,
  "user": "user-1234",
  "messages": [
    {
      "content": "string",
      "role": "developer",
      "name": "string"
    }
  ],
  "model": "gpt-4o",
  "modalities": [
    "text"
  ],
  "reasoning_effort": "medium",
  "max_completion_tokens": 42,
  "frequency_penalty": 0,
  "presence_penalty": 0,
  "web_search_options": {
    "user_location": {
      "type": "approximate",
      "approximate": {
        "country": "string",
        "region": "string",
        "city": "string",
        "timezone": "string"
      }
    },
    "search_context_size": "medium"
  },
  "top_logprobs": 42,
  "response_format": {
    "type": "text"
  },
  "service_tier": "auto",
  "audio": {
    "voice": "ash",
    "format": "wav"
  },
  "store": false,
  "stream": false,
  "stop": "<|endoftext|>",
  "logit_bias": {
    "additionalProperty1": 42,
    "additionalProperty2": 42
  },
  "logprobs": false,
  "max_tokens": 42,
  "n": 1,
  "prediction": {
    "type": "content",
    "content": "string"
  },
  "seed": 42,
  "stream_options": {
    "include_usage": true
  },
  "tools": [
    {
      "type": "function",
      "function": {
        "description": "string",
        "name": "string",
        "parameters": {},
        "strict": false
      }
    }
  ],
  "tool_choice": "none",
  "parallel_tool_calls": true,
  "function_call": "none",
  "functions": [
    {
      "description": "string",
      "name": "string",
      "parameters": {}
    }
  ]
}

Response examples (200)

{
  "id": "string",
  "choices": [
    {
      "finish_reason": "stop",
      "index": 42,
      "message": {
        "content": "string",
        "refusal": "string",
        "tool_calls": [
          {
            "id": "string",
            "type": "function",
            "function": {
              "name": "string",
              "arguments": "string"
            }
          }
        ],
        "annotations": [
          {
            "type": "url_citation",
            "url_citation": {
              "end_index": 42,
              "start_index": 42,
              "url": "string",
              "title": "string"
            }
          }
        ],
        "role": "assistant",
        "function_call": {
          "arguments": "string",
          "name": "string"
        },
        "audio": {
          "id": "string",
          "expires_at": 42,
          "data": "string",
          "transcript": "string"
        }
      },
      "logprobs": {
        "content": [
          {
            "token": "string",
            "logprob": 42.0,
            "bytes": [
              42
            ],
            "top_logprobs": [
              {
                "token": "string",
                "logprob": 42.0,
                "bytes": [
                  42
                ]
              }
            ]
          }
        ],
        "refusal": [
          {
            "token": "string",
            "logprob": 42.0,
            "bytes": [
              42
            ],
            "top_logprobs": [
              {
                "token": "string",
                "logprob": 42.0,
                "bytes": [
                  42
                ]
              }
            ]
          }
        ]
      }
    }
  ],
  "created": 42,
  "model": "string",
  "service_tier": "scale",
  "system_fingerprint": "string",
  "object": "chat.completion",
  "usage": {
    "completion_tokens": 0,
    "prompt_tokens": 0,
    "total_tokens": 0,
    "completion_tokens_details": {
      "accepted_prediction_tokens": 0,
      "audio_tokens": 0,
      "reasoning_tokens": 0,
      "rejected_prediction_tokens": 0
    },
    "prompt_tokens_details": {
      "audio_tokens": 0,
      "cached_tokens": 0
    }
  }
}

Body Required

model string Required

response_format object

voice string Required

stop string | null | array[string]

content string | array[object] Required

tool_choice string | object

function_call string | object Deprecated

Responses