Create chat completion

POSThttps:/api.openai.com/v1/chat/completions

Starting a new project? We recommend trying Responses to take advantage of the latest OpenAI platform features. Compare Chat Completions with Responses.

Creates a model response for the given chat conversation. Learn more in the text generation, vision, and 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.

Request body

metadata
object or 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.
temperature
number or null
Defaults: 1
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.
top_p
number or null
Defaults: 1
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.
user
string
A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse. Learn more.
service_tier
string or null
Defaults: auto
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.
- If set to 'flex', the request will be processed with the Flex Processing service tier. Learn more.
- When not set, the default behavior is 'auto'.
When this parameter is set, the response body will include the service_tier utilized.
- auto
  string
- default
  string
- flex
  string
messages
array
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.
- Developer message
  object
  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.
  content
  string or array
  The contents of the developer message.
  Text content
  string
  Required
  The contents of the developer message.
  Array of content parts
  array
  Required
  An array of content parts with a defined type. For developer messages, only type text is supported.
  items
  object
  Learn about text inputs.
  type
  string
  Required
  The type of the content part.
  text
  string
  text
  string
  Required
  The text content.
  role
  string
  Required
  The role of the messages author, in this case developer.
  developer
  string
  name
  string
  An optional name for the participant. Provides the model information to differentiate between participants of the same role.
- System message
  object
  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.
  content
  string or array
  The contents of the system message.
  Text content
  string
  Required
  The contents of the system message.
  Array of content parts
  array
  Required
  An array of content parts with a defined type. For system messages, only type text is supported.
  Text content part
  object
  Learn about text inputs.
  type
  string
  Required
  The type of the content part.
  text
  string
  text
  string
  Required
  The text content.
  role
  string
  Required
  The role of the messages author, in this case system.
  system
  string
  name
  string
  An optional name for the participant. Provides the model information to differentiate between participants of the same role.
- User message
  object
  Messages sent by an end user, containing prompts or additional context information.
  content
  string or array
  The contents of the user message.
  Text content
  string
  Required
  The text contents of the message.
  Array of content parts
  array
  Required
  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.
  Text content part
  object
  Learn about text inputs.
  type
  string
  Required
  The type of the content part.
  text
  string
  text
  string
  Required
  The text content.
  Image content part
  object
  Learn about image inputs.
  type
  string
  Required
  The type of the content part.
  image_url
  string
  image_url
  object
  Required
  url
  string
  Required
  Either a URL of the image or the base64 encoded image data.
  detail
  string
  Defaults: auto
  Specifies the detail level of the image. Learn more in the Vision guide.
  auto
  string
  low
  string
  high
  string
  Audio content part
  object
  Learn about audio inputs.
  type
  string
  Required
  The type of the content part. Always input_audio.
  input_audio
  string
  input_audio
  object
  Required
  data
  string
  Required
  Base64 encoded audio data.
  format
  string
  Required
  The format of the encoded audio data. Currently supports "wav" and "mp3".
  wav
  string
  mp3
  string
  File content part
  object
  Learn about file inputs for text generation.
  type
  string
  Required
  The type of the content part. Always file.
  file
  string
  file
  object
  Required
  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.
  user
  string
  name
  string
  An optional name for the participant. Provides the model information to differentiate between participants of the same role.
- Assistant message
  object
  Messages sent by the model in response to user messages.
  content
  string or array
  The contents of the assistant message. Required unless tool_calls or function_call is specified.
  Text content
  string
  The contents of the assistant message.
  Array of content parts
  array
  An array of content parts with a defined type. Can be one or more of type text, or exactly one of type refusal.
  Text content part
  object
  Learn about text inputs.
  type
  string
  Required
  The type of the content part.
  text
  string
  text
  string
  Required
  The text content.
  Refusal content part
  object
  type
  string
  Required
  The type of the content part.
  refusal
  string
  refusal
  string
  Required
  The refusal message generated by the model.
  refusal
  string or null
  The refusal message by the assistant.
  role
  string
  Required
  The role of the messages author, in this case assistant.
  assistant
  string
  name
  string
  An optional name for the participant. Provides the model information to differentiate between participants of the same role.
  audio
  object or null
  Data about a previous audio response from the model. Learn more.
  id
  string
  Required
  Unique identifier for a previous audio response from the model.
  tool_calls
  array
  The tool calls generated by the model, such as function calls.
  items
  object
  id
  string
  Required
  The ID of the tool call.
  type
  string
  Required
  The type of the tool. Currently, only function is supported.
  function
  string
  function
  object
  Required
  The function that the model called.
  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 or null
  Deprecated
  Deprecated and replaced by tool_calls. The name and arguments of a function that should be called, as generated by the model.
  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.
- Tool message
  object
  role
  string
  Required
  The role of the messages author, in this case tool.
  tool
  string
  content
  string or array
  The contents of the tool message.
  Text content
  string
  Required
  The contents of the tool message.
  Array of content parts
  array
  Required
  An array of content parts with a defined type. For tool messages, only type text is supported.
  Text content part
  object
  Learn about text inputs.
  type
  string
  Required
  The type of the content part.
  text
  string
  text
  string
  Required
  The text content.
  tool_call_id
  string
  Required
  Tool call that this message is responding to.
- Function message
  object
  Deprecated
  role
  string
  Required
  The role of the messages author, in this case function.
  function
  string
  content
  string or null
  Required
  The contents of the function message.
  name
  string
  Required
  The name of the function to call.
model
string
Model ID used to generate the response, like gpt-4o or o3. 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.
- model
  string
  Required
- model
  string
  Required
  gpt-4.1
  string
  gpt-4.1-mini
  string
  gpt-4.1-nano
  string
  gpt-4.1-2025-04-14
  string
  gpt-4.1-mini-2025-04-14
  string
  gpt-4.1-nano-2025-04-14
  string
  o4-mini
  string
  o4-mini-2025-04-16
  string
  o3
  string
  o3-2025-04-16
  string
  o3-mini
  string
  o3-mini-2025-01-31
  string
  o1
  string
  o1-2024-12-17
  string
  o1-preview
  string
  o1-preview-2024-09-12
  string
  o1-mini
  string
  o1-mini-2024-09-12
  string
  gpt-4o
  string
  gpt-4o-2024-11-20
  string
  gpt-4o-2024-08-06
  string
  gpt-4o-2024-05-13
  string
  gpt-4o-audio-preview
  string
  gpt-4o-audio-preview-2024-10-01
  string
  gpt-4o-audio-preview-2024-12-17
  string
  gpt-4o-mini-audio-preview
  string
  gpt-4o-mini-audio-preview-2024-12-17
  string
  gpt-4o-search-preview
  string
  gpt-4o-mini-search-preview
  string
  gpt-4o-search-preview-2025-03-11
  string
  gpt-4o-mini-search-preview-2025-03-11
  string
  chatgpt-4o-latest
  string
  gpt-4o-mini
  string
  gpt-4o-mini-2024-07-18
  string
  gpt-4-turbo
  string
  gpt-4-turbo-2024-04-09
  string
  gpt-4-0125-preview
  string
  gpt-4-turbo-preview
  string
  gpt-4-1106-preview
  string
  gpt-4-vision-preview
  string
  gpt-4
  string
  gpt-4-0314
  string
  gpt-4-0613
  string
  gpt-4-32k
  string
  gpt-4-32k-0314
  string
  gpt-4-32k-0613
  string
  gpt-3.5-turbo
  string
  gpt-3.5-turbo-16k
  string
  gpt-3.5-turbo-0301
  string
  gpt-3.5-turbo-0613
  string
  gpt-3.5-turbo-1106
  string
  gpt-3.5-turbo-0125
  string
  gpt-3.5-turbo-16k-0613
  string
modalities
array or 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"]
- items
  string
  text
  string
  audio
  string
reasoning_effort
string or null
Defaults: medium
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.
- low
  string
- medium
  string
- high
  string
max_completion_tokens
integer or 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 or null
Defaults: 0
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.
presence_penalty
number or null
Defaults: 0
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.
web_search_options
object
This tool searches the web for relevant results to use in a response. Learn more about the web search tool.
- user_location
  object or null
  Approximate location parameters for the search.
  type
  string
  Required
  The type of location approximation. Always approximate.
  approximate
  string
  approximate
  object
  Required
  Approximate location parameters for the search.
  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
  Defaults: medium
  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.
  low
  string
  medium
  string
  high
  string
top_logprobs
integer or 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.
response_format
object
An object specifying the format that the model must output.
Setting to enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the Structured Outputs guide.
Setting to 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.
- Text
  object
  Default response format. Used to generate text responses.
  type
  string
  Required
  The type of response format being defined. Always text.
  text
  string
- JSON schema
  object
  JSON Schema response format. Used to generate structured JSON responses. Learn more about Structured Outputs.
  type
  string
  Required
  The type of response format being defined. Always json_schema.
  json_schema
  string
  json_schema
  object
  Required
  Structured Outputs configuration options, including a JSON Schema.
  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.
  strict
  boolean or null
  Defaults: false
  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.
- JSON object
  object
  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.
  type
  string
  Required
  The type of response format being defined. Always json_object.
  json_object
  string
audio
object or null
Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.
- voice
  string
  The voice the model uses to respond. Supported voices are alloy, ash, ballad, coral, echo, fable, nova, onyx, sage, and shimmer.
  voice
  string
  Required
  voice
  string
  Required
  alloy
  string
  ash
  string
  ballad
  string
  coral
  string
  echo
  string
  fable
  string
  onyx
  string
  nova
  string
  sage
  string
  shimmer
  string
  verse
  string
- format
  string
  Required
  Specifies the output audio format. Must be one of wav, mp3, flac, opus, or pcm16.
  wav
  string
  aac
  string
  mp3
  string
  flac
  string
  opus
  string
  pcm16
  string
store
boolean or null
Defaults: false
Whether or not to store the output of this chat completion request for use in our model distillation or evals products.
stream
boolean or null
Defaults: false
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.
stop
string or array
Not supported with latest reasoning models o3 and o4-mini.
Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence.
- stop
  string or null
  Defaults: <|endoftext|>
- stop
  array
  items
  string
logit_bias
object or null
Defaults: 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.
logprobs
boolean or null
Defaults: false
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_tokens
integer or 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 o-series models.
n
integer or null
Defaults: 1
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.
prediction
object
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.
- Static Content
  object
  Static predicted output content, such as the content of a text file that is being regenerated.
  type
  string
  Required
  The type of the predicted content you want to provide. This type is currently always content.
  content
  string
  content
  string or array
  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.
  Text content
  string
  Required
  The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes.
  Array of content parts
  array
  Required
  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.
  items
  object
  Learn about text inputs.
  type
  string
  Required
  The type of the content part.
  text
  string
  text
  string
  Required
  The text content.
seed
integer or 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 or null
Defaults: null
Options for streaming response. Only set this when you set stream: true.
- 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
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.
- items
  object
  type
  string
  Required
  The type of the tool. Currently, only function is supported.
  function
  string
  function
  object
  Required
  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.
  strict
  boolean or null
  Defaults: false
  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 .
tool_choice
string or 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 forces the model to call that tool.
none is the default when no tools are present. auto is the default if tools are present.
- tool_choice
  string
  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.
  none
  string
  auto
  string
  required
  string
- tool_choice
  object
  Specifies a tool the model should use. Use to force the model to call a specific function.
  type
  string
  Required
  The type of the tool. Currently, only function is supported.
  function
  string
  function
  object
  Required
  name
  string
  Required
  The name of the function to call.
parallel_tool_calls
boolean
Defaults: true
Whether to enable parallel function calling during tool use.
function_call
string or object
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 forces the model to call that function.
none is the default when no functions are present. auto is the default if functions are present.
- function_call
  string
  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.
  none
  string
  auto
  string
- function_call
  object
  Specifying a particular function via forces the model to call that function.
  name
  string
  Required
  The name of the function to call.
functions
array
Deprecated
Deprecated in favor of tools.
A list of functions the model may generate JSON inputs for.
- items
  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.

Response

Returns a chat completion object, or a streamed sequence of chat completion chunk objects if the request is streamed.

Example request

1curl https://api.openai.com/v1/chat/completions \
2  -H "Content-Type: application/json" \
3  -H "Authorization: Bearer $OPENAI_API_KEY" \
4  -d '{
5    "model": "VAR_chat_model_id",
6    "messages": [
7      {
8        "role": "developer",
9        "content": "You are a helpful assistant."
10      },
11      {
12        "role": "user",
13        "content": "Hello!"
14      }
15    ]
16  }'

Example response

1{
2  "id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
3  "object": "chat.completion",
4  "created": 1741569952,
5  "model": "gpt-4.1-2025-04-14",
6  "choices": [
7    {
8      "index": 0,
9      "message": {
10        "role": "assistant",
11        "content": "Hello! How can I assist you today?",
12        "refusal": null,
13        "annotations": []
14      },
15      "logprobs": null,
16      "finish_reason": "stop"
17    }
18  ],
19  "usage": {
20    "prompt_tokens": 19,
21    "completion_tokens": 10,
22    "total_tokens": 29,
23    "prompt_tokens_details": {
24      "cached_tokens": 0,
25      "audio_tokens": 0
26    },
27    "completion_tokens_details": {
28      "reasoning_tokens": 0,
29      "audio_tokens": 0,
30      "accepted_prediction_tokens": 0,
31      "rejected_prediction_tokens": 0
32    }
33  },
34  "service_tier": "default"
35}

Built with