Create chat completion
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.
Body ParametersJSON
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.
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.
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.
An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens.
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.
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.
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.
Whether to enable parallel function calling during tool use.
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.
Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the user field. Learn more.
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. We recommend hashing their username or email address, in order to avoid sending us any identifying information. Learn more.
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.
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.
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.
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.
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.
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.
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.
Returns
Create chat completion
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "VAR_chat_model_id",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'
{
"id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
"object": "chat.completion",
"created": 1741569952,
"model": "gpt-4.1-2025-04-14",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I assist you today?",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 19,
"completion_tokens": 10,
"total_tokens": 29,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default"
}
Create chat completion
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-4.1",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What is in this image?"
},
{
"type": "image_url",
"image_url": {
"url": "https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg"
}
}
]
}
],
"max_tokens": 300
}'
{
"id": "chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG",
"object": "chat.completion",
"created": 1741570283,
"model": "gpt-4.1-2025-04-14",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds, giving the scene a serene and peaceful atmosphere. Trees and shrubs are visible in the background.",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 1117,
"completion_tokens": 46,
"total_tokens": 1163,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default"
}
Create chat completion
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "VAR_chat_model_id",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
],
"stream": true
}'
{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]}
{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]}
....
{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
Create chat completion
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-4.1",
"messages": [
{
"role": "user",
"content": "What is the weather like in Boston today?"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location"]
}
}
}
],
"tool_choice": "auto"
}'
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1699896916,
"model": "gpt-4o-mini",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": null,
"tool_calls": [
{
"id": "call_abc123",
"type": "function",
"function": {
"name": "get_current_weather",
"arguments": "{\n\"location\": \"Boston, MA\"\n}"
}
}
]
},
"logprobs": null,
"finish_reason": "tool_calls"
}
],
"usage": {
"prompt_tokens": 82,
"completion_tokens": 17,
"total_tokens": 99,
"completion_tokens_details": {
"reasoning_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
}
}
Create chat completion
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "VAR_chat_model_id",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"logprobs": true,
"top_logprobs": 2
}'
{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1702685778,
"model": "gpt-4o-mini",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I assist you today?"
},
"logprobs": {
"content": [
{
"token": "Hello",
"logprob": -0.31725305,
"bytes": [72, 101, 108, 108, 111],
"top_logprobs": [
{
"token": "Hello",
"logprob": -0.31725305,
"bytes": [72, 101, 108, 108, 111]
},
{
"token": "Hi",
"logprob": -1.3190403,
"bytes": [72, 105]
}
]
},
{
"token": "!",
"logprob": -0.02380986,
"bytes": [
33
],
"top_logprobs": [
{
"token": "!",
"logprob": -0.02380986,
"bytes": [33]
},
{
"token": " there",
"logprob": -3.787621,
"bytes": [32, 116, 104, 101, 114, 101]
}
]
},
{
"token": " How",
"logprob": -0.000054669687,
"bytes": [32, 72, 111, 119],
"top_logprobs": [
{
"token": " How",
"logprob": -0.000054669687,
"bytes": [32, 72, 111, 119]
},
{
"token": "<|end|>",
"logprob": -10.953937,
"bytes": null
}
]
},
{
"token": " can",
"logprob": -0.015801601,
"bytes": [32, 99, 97, 110],
"top_logprobs": [
{
"token": " can",
"logprob": -0.015801601,
"bytes": [32, 99, 97, 110]
},
{
"token": " may",
"logprob": -4.161023,
"bytes": [32, 109, 97, 121]
}
]
},
{
"token": " I",
"logprob": -3.7697225e-6,
"bytes": [
32,
73
],
"top_logprobs": [
{
"token": " I",
"logprob": -3.7697225e-6,
"bytes": [32, 73]
},
{
"token": " assist",
"logprob": -13.596657,
"bytes": [32, 97, 115, 115, 105, 115, 116]
}
]
},
{
"token": " assist",
"logprob": -0.04571125,
"bytes": [32, 97, 115, 115, 105, 115, 116],
"top_logprobs": [
{
"token": " assist",
"logprob": -0.04571125,
"bytes": [32, 97, 115, 115, 105, 115, 116]
},
{
"token": " help",
"logprob": -3.1089056,
"bytes": [32, 104, 101, 108, 112]
}
]
},
{
"token": " you",
"logprob": -5.4385737e-6,
"bytes": [32, 121, 111, 117],
"top_logprobs": [
{
"token": " you",
"logprob": -5.4385737e-6,
"bytes": [32, 121, 111, 117]
},
{
"token": " today",
"logprob": -12.807695,
"bytes": [32, 116, 111, 100, 97, 121]
}
]
},
{
"token": " today",
"logprob": -0.0040071653,
"bytes": [32, 116, 111, 100, 97, 121],
"top_logprobs": [
{
"token": " today",
"logprob": -0.0040071653,
"bytes": [32, 116, 111, 100, 97, 121]
},
{
"token": "?",
"logprob": -5.5247097,
"bytes": [63]
}
]
},
{
"token": "?",
"logprob": -0.0008108172,
"bytes": [63],
"top_logprobs": [
{
"token": "?",
"logprob": -0.0008108172,
"bytes": [63]
},
{
"token": "?\n",
"logprob": -7.184561,
"bytes": [63, 10]
}
]
}
]
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 9,
"total_tokens": 18,
"completion_tokens_details": {
"reasoning_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"system_fingerprint": null
}
Returns Examples
{
"id": "id",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"logprobs": {
"content": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
],
"refusal": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0,
"top_logprobs": [
{
"token": "token",
"bytes": [
0
],
"logprob": 0
}
]
}
]
},
"message": {
"content": "content",
"refusal": "refusal",
"role": "assistant",
"annotations": [
{
"type": "url_citation",
"url_citation": {
"end_index": 0,
"start_index": 0,
"title": "title",
"url": "url"
}
}
],
"audio": {
"id": "id",
"data": "data",
"expires_at": 0,
"transcript": "transcript"
},
"function_call": {
"arguments": "arguments",
"name": "name"
},
"tool_calls": [
{
"id": "id",
"function": {
"arguments": "arguments",
"name": "name"
},
"type": "function"
}
]
}
}
],
"created": 0,
"model": "model",
"object": "chat.completion",
"service_tier": "auto",
"system_fingerprint": "system_fingerprint",
"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
}
}
}