Create chat completion

$ openai chat:completions create

POST/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.

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

ParametersExpand Collapse

--message: array of ChatCompletionMessageParam

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.

--model: string or ChatModel

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.

--audio: optional object { format, voice }

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]. Learn more.

--frequency-penalty: optional number

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.

Deprecated--function-call: optional "none" or "auto" or ChatCompletionFunctionCallOption { name }

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.

Deprecated--function: optional array of object { name, description, parameters }

Deprecated in favor of tools.

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

--logit-bias: optional map[number]

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: optional boolean

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: optional number

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

Deprecated--max-tokens: optional number

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.

--metadata: optional map[string]

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.

--modality: optional array of "text" or "audio"

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"]

--n: optional number

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.

--parallel-tool-calls: optional boolean

Whether to enable parallel function calling during tool use.

--prediction: optional object { content, type }

Static predicted output content, such as the content of a text file that is being regenerated.

--presence-penalty: optional number

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: optional string

Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.

--prompt-cache-retention: optional "in_memory" or "24h"

The retention policy for the prompt cache. Set to 24h to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. Learn more.

--reasoning-effort: optional "none" or "minimal" or "low" or 3 more

Constrains effort on reasoning for reasoning models. Currently supported values are none, minimal, low, medium, high, and xhigh. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response.

gpt-5.1 defaults to none, which does not perform reasoning. The supported reasoning values for gpt-5.1 are none, low, medium, and high. Tool calls are supported for all reasoning values in gpt-5.1.
All models before gpt-5.1 default to medium reasoning effort, and do not support none.
The gpt-5-pro model defaults to (and only supports) high reasoning effort.
xhigh is supported for all models after gpt-5.1-codex-max.

--response-format: optional ResponseFormatText { type } or ResponseFormatJSONSchema { json_schema, type } or ResponseFormatJSONObject { type }

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.

--safety-identifier: optional string

A stable identifier used to help detect users of your application that may be violating OpenAI’s usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.

Deprecated--seed: optional number

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.

--service-tier: optional "auto" or "default" or "flex" or 2 more

Specifies the processing type used for serving the request.

If set to ‘auto’, then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use ‘default’.
If set to ‘default’, then the request will be processed with the standard pricing and performance for the selected model.
If set to ‘flex’ or ‘priority’, then the request will be processed with the corresponding service tier.
When not set, the default behavior is ‘auto’.

When the service_tier parameter is set, the response body will include the service_tier value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.

--stop: optional string or array of string

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.

--store: optional boolean

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

Supports text and image inputs. Note: image inputs over 8MB will be dropped.

--stream-options: optional object { include_obfuscation, include_usage }

Options for streaming response. Only set this when you set stream: true.

--temperature: optional number

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.

--tool-choice: optional "none" or "auto" or "required" or ChatCompletionAllowedToolChoice { allowed_tools, type } or ChatCompletionNamedToolChoice { function, type } or ChatCompletionNamedToolChoiceCustom { custom, type }

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.

--tool: optional array of ChatCompletionTool

A list of tools the model may call. You can provide either custom tools or function tools.

--top-logprobs: optional number

An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. logprobs must be set to true if this parameter is used.

--top-p: optional number

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.

Deprecated--user: optional string

This field is being replaced by safety_identifier and prompt_cache_key. Use prompt_cache_key instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. Learn more.

--verbosity: optional "low" or "medium" or "high"

Constrains the verbosity of the model’s response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are low, medium, and high.

--web-search-options: optional object { search_context_size, user_location }

This tool searches the web for relevant results to use in a response. Learn more about the web search tool.

ReturnsExpand Collapse

chat_completion: object { id, choices, created, 5 more }

Represents a chat completion response returned by model, based on the provided input.

id: string

A unique identifier for the chat completion.

choices: array of object { finish_reason, index, logprobs, message }

A list of chat completion choices. Can be more than one if n is greater than 1.

finish_reason: "stop" or "length" or "tool_calls" or 2 more

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.

"stop"

"length"

"tool_calls"

"content_filter"

"function_call"

index: number

The index of the choice in the list of choices.

logprobs: object { content, refusal }

Log probability information for the choice.

content: array of ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs }

A list of message content tokens with log probability information.

token: string

The token.

bytes: array of number

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.

logprob: number

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.

top_logprobs: array of object { token, bytes, logprob }

List of the most likely tokens and their log probability, at this token position. The number of entries may be fewer than the requested top_logprobs.

token: string

The token.

bytes: array of number

logprob: number

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.

refusal: array of ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs }

A list of message refusal tokens with log probability information.

token: string

The token.

bytes: array of number

logprob: number

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.

top_logprobs: array of object { token, bytes, logprob }

List of the most likely tokens and their log probability, at this token position. The number of entries may be fewer than the requested top_logprobs.

token: string

The token.

bytes: array of number

logprob: number

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.

message: object { content, refusal, role, 4 more }

A chat completion message generated by the model.

content: string

The contents of the message.

refusal: string

The refusal message generated by the model.

role: "assistant"

The role of the author of this message.

annotations: optional array of object { type, url_citation }

Annotations for the message, when applicable, as when using the web search tool.

type: "url_citation"

The type of the URL citation. Always url_citation.

url_citation: object { end_index, start_index, title, url }

A URL citation when using web search.

end_index: number

The index of the last character of the URL citation in the message.

start_index: number

The index of the first character of the URL citation in the message.

title: string

The title of the web resource.

url: string

The URL of the web resource.

audio: optional object { id, data, expires_at, transcript }

If the audio output modality is requested, this object contains data about the audio response from the model. Learn more.

id: string

Unique identifier for this audio response.

data: string

Base64 encoded audio bytes generated by the model, in the format specified in the request.

expires_at: number

The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations.

transcript: string

Transcript of the audio generated by the model.

Deprecatedfunction_call: optional object { arguments, name }

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

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.

The name of the function to call.

tool_calls: optional array of ChatCompletionMessageToolCall

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

chat_completion_message_function_tool_call: object { id, function, type }

A call to a function tool created by the model.

id: string

The ID of the tool call.

function: object { arguments, name }

The function that the model called.

arguments: string

The name of the function to call.

type: "function"

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

chat_completion_message_custom_tool_call: object { id, custom, type }

A call to a custom tool created by the model.

id: string

The ID of the tool call.

custom: object { input, name }

The custom tool that the model called.

input: string

The input for the custom tool call generated by the model.

The name of the custom tool to call.

type: "custom"

The type of the tool. Always custom.

created: number

The Unix timestamp (in seconds) of when the chat completion was created.

model: string

The model used for the chat completion.

object: "chat.completion"

The object type, which is always chat.completion.

service_tier: optional "auto" or "default" or "flex" or 2 more

Specifies the processing type used for serving the request.

If set to ‘auto’, then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use ‘default’.
If set to ‘default’, then the request will be processed with the standard pricing and performance for the selected model.
If set to ‘flex’ or ‘priority’, then the request will be processed with the corresponding service tier.
When not set, the default behavior is ‘auto’.

"auto"

"default"

"flex"

"scale"

"priority"

Deprecatedsystem_fingerprint: optional 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.

usage: optional object { completion_tokens, prompt_tokens, total_tokens, 2 more }

Usage statistics for the completion request.

completion_tokens: number

Number of tokens in the generated completion.

prompt_tokens: number

Number of tokens in the prompt.

total_tokens: number

Total number of tokens used in the request (prompt + completion).

completion_tokens_details: optional object { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }

Breakdown of tokens used in a completion.

accepted_prediction_tokens: optional number

When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.

audio_tokens: optional number

Audio input tokens generated by the model.

reasoning_tokens: optional number

Tokens generated by the model for reasoning.

rejected_prediction_tokens: optional number

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.

prompt_tokens_details: optional object { audio_tokens, cached_tokens }

Breakdown of tokens used in the prompt.

audio_tokens: optional number

Audio input tokens present in the prompt.

cached_tokens: optional number

Cached tokens present in the prompt.

chat_completion_chunk: object { id, choices, created, 5 more }

Represents a streamed chunk of a chat completion response returned by the model, based on the provided input. Learn more.

id: string

A unique identifier for the chat completion. Each chunk has the same ID.

choices: array of object { delta, finish_reason, index, logprobs }

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}.

delta: object { content, function_call, refusal, 2 more }

A chat completion delta generated by streamed model responses.

content: optional string

The contents of the chunk message.

Deprecatedfunction_call: optional object { arguments, name }

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

arguments: optional string

The name of the function to call.

refusal: optional string

The refusal message generated by the model.

role: optional "developer" or "system" or "user" or 2 more

The role of the author of this message.

"developer"

"system"

"user"

"assistant"

"tool"

tool_calls: optional array of object { index, id, function, type }

index: number

id: optional string

The ID of the tool call.

function: optional object { arguments, name }

arguments: optional string

The name of the function to call.

type: optional "function"

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

"function"

finish_reason: "stop" or "length" or "tool_calls" or 2 more

"stop"

"length"

"tool_calls"

"content_filter"

"function_call"

index: number

The index of the choice in the list of choices.

logprobs: optional object { content, refusal }

Log probability information for the choice.

content: array of ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs }

A list of message content tokens with log probability information.

token: string

The token.

bytes: array of number

logprob: number

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.

top_logprobs: array of object { token, bytes, logprob }

List of the most likely tokens and their log probability, at this token position. The number of entries may be fewer than the requested top_logprobs.

token: string

The token.

bytes: array of number

logprob: number

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.

refusal: array of ChatCompletionTokenLogprob { token, bytes, logprob, top_logprobs }

A list of message refusal tokens with log probability information.

token: string

The token.

bytes: array of number

logprob: number

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.

top_logprobs: array of object { token, bytes, logprob }

List of the most likely tokens and their log probability, at this token position. The number of entries may be fewer than the requested top_logprobs.

token: string

The token.

bytes: array of number

logprob: number

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.

created: number

The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp.

model: string

The model to generate the completion.

object: "chat.completion.chunk"

The object type, which is always chat.completion.chunk.

service_tier: optional "auto" or "default" or "flex" or 2 more

Specifies the processing type used for serving the request.

If set to ‘auto’, then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use ‘default’.
If set to ‘default’, then the request will be processed with the standard pricing and performance for the selected model.
If set to ‘flex’ or ‘priority’, then the request will be processed with the corresponding service tier.
When not set, the default behavior is ‘auto’.

"auto"

"default"

"flex"

"scale"

"priority"

Deprecatedsystem_fingerprint: optional 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.

usage: optional object { completion_tokens, prompt_tokens, total_tokens, 2 more }

An optional field that will only be present when you set stream_options: {"include_usage": true} in your request. When present, it contains a null value except for the last chunk which contains the token usage statistics for the entire request.

NOTE: If the stream is interrupted or cancelled, you may not receive the final usage chunk which contains the total token usage for the request.

completion_tokens: number

Number of tokens in the generated completion.

prompt_tokens: number

Number of tokens in the prompt.

total_tokens: number

Total number of tokens used in the request (prompt + completion).

completion_tokens_details: optional object { accepted_prediction_tokens, audio_tokens, reasoning_tokens, rejected_prediction_tokens }

Breakdown of tokens used in a completion.

accepted_prediction_tokens: optional number

When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion.

audio_tokens: optional number

Audio input tokens generated by the model.

reasoning_tokens: optional number

Tokens generated by the model for reasoning.

rejected_prediction_tokens: optional number

prompt_tokens_details: optional object { audio_tokens, cached_tokens }

Breakdown of tokens used in the prompt.

audio_tokens: optional number

Audio input tokens present in the prompt.

cached_tokens: optional number

Cached tokens present in the prompt.