NAME
OpenAPI::Client::OpenAI::Path::chat-completions - Documentation for the /chat/completions path.
DESCRIPTION
This document describes the API endpoint at /chat/completions
.
See the examples/
directory in the distribution for examples of how to use this.
GET /chat/completions
List stored Chat Completions. Only Chat Completions that have been stored with the `store` parameter set to `true` will be returned.
Operation ID
listChatCompletions
$client->listChatCompletions( ... );
Parameters
model
(in query) (Optional) - The model used to generate the Chat Completions. Type:string
metadata
(in query) (Optional) - A list of metadata keys to filter the Chat Completions by. Example:`metadata[key1]=value1&metadata[key2]=value2`
Type:
object
after
(in query) (Optional) - Identifier for the last chat completion from the previous pagination request. Type:string
limit
(in query) (Optional) - Number of Chat Completions to retrieve. Type:integer
Default:
20
order
(in query) (Optional) - Sort order for Chat Completions by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`. Type:string
Possible values:
asc desc
Default:
asc
Responses
Status Code: 200
A list of Chat Completions
Content Types:
application/json
Example:
{ "data" : [ { "service_tier" : "scale", "usage" : { "completion_tokens_details" : null, "prompt_tokens_details" : null }, "choices" : [ { "message" : { "tool_calls" : [ { "function" : null } ], "audio" : null, "function_call" : null, "annotations" : [ { "url_citation" : null } ] }, "logprobs" : { "content" : [ { "top_logprobs" : [ { "bytes" : [ null ] } ], "bytes" : [ null ] } ], "refusal" : [ { "bytes" : [ null ], "top_logprobs" : [ { "bytes" : [ null ] } ] } ] } } ] } ] }
POST /chat/completions
**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).
Operation ID
createChatCompletion
$client->createChatCompletion( ... );
Request Body
Content Type: application/json
Responses
Status Code: 200
OK
Content Types:
application/json
Example:
{ "service_tier" : "scale", "choices" : [ { "logprobs" : { "content" : [ { "top_logprobs" : [ { "bytes" : [ null ] } ], "bytes" : [ null ] } ], "refusal" : [ { "top_logprobs" : [ { "bytes" : [ null ] } ], "bytes" : [ null ] } ] }, "message" : { "tool_calls" : [ { "function" : null } ], "audio" : null, "function_call" : null, "annotations" : [ { "url_citation" : null } ] } } ], "usage" : { "prompt_tokens_details" : null, "completion_tokens_details" : null } }
text/event-stream
Example:
{ "choices" : [ { "delta" : { "tool_calls" : [ { "function" : null } ], "function_call" : null }, "logprobs" : { "refusal" : [ { "bytes" : [ null ], "top_logprobs" : [ { "bytes" : [ null ] } ] } ], "content" : [ { "top_logprobs" : [ { "bytes" : [ null ] } ], "bytes" : [ null ] } ] } } ], "usage" : { "prompt_tokens_details" : null, "completion_tokens_details" : null }, "service_tier" : "scale" }
SEE ALSO
COPYRIGHT AND LICENSE
Copyright (C) 2023-2025 by Nelson Ferraz
This library is free software; you can redistribute it and/or modify it under the same terms as Perl itself, either Perl version 5.14.0 or, at your option, any later version of Perl 5 you may have available.