ChatCompletionsFormat

POST /v1/chat/completions

Request Parameters

Parameter	Type	Required	Description
model	string	Required	Model ID
messages	array<object>	Required	Conversation message list
messages[].role	string	Required	Message role
messages[].content	string | array<object>	Required	Message content
messages[].name	string	Optional	Sender name
messages[].tool_calls	array<object>	Optional	-
messages[].tool_calls[].id	string	Optional	-
messages[].tool_calls[].type	string	Optional	-
messages[].tool_calls[].function	object	Optional	-
messages[].tool_call_id	string	Optional	Tool call ID (for tool role messages)
messages[].reasoning_content	string	Optional	Reasoning content
temperature	number	Optional	Sampling temperature
top_p	number	Optional	Top-p sampling parameter
n	integer	Optional	Number of completions to generate
stream	boolean	Optional	Whether to stream the response
stream_options	object	Optional	-
stream_options.include_usage	boolean	Optional	-
stop	string | array<string>	Optional	Stop sequences
max_tokens	integer	Optional	Maximum tokens to generate
max_completion_tokens	integer	Optional	Maximum completion tokens
presence_penalty	number	Optional	-
frequency_penalty	number	Optional	-
logit_bias	object	Optional	-
user	string	Optional	-
tools	array<object>	Optional	-
tools[].type	string	Optional	-
tools[].function	object	Optional	-
tools[].function.name	string	Optional	-
tools[].function.description	string	Optional	-
tools[].function.parameters	object	Optional	Parameter definitions in JSON Schema format
tool_choice	string | object	Optional	-
response_format	object	Optional	-
response_format.type	string	Optional	-
response_format.json_schema	object	Optional	JSON Schema definition
seed	integer	Optional	-
reasoning_effort	string	Optional	Reasoning effort (for models that support reasoning)
modalities	array<string>	Optional	-
audio	object	Optional	-
audio.voice	string	Optional	-
audio.format	string	Optional	-

Request Example

{
  "body": {
    "model": "gpt-4",
    "messages": [
      {
        "role": "system",
        "content": "string"
      }
    ]
  }
}

Response Fields（200）

Field Name	Type	Description
model	string	p p-0 Model ID
messages	array<object>	p p-0 Conversation message list
messages[].role	string	p p-0 Message role
messages[].content	string | array<object>	p p-0 Message content
messages[].name	string	p p-0 Sender name
messages[].tool_calls	array<object>	-
messages[].tool_calls[].id	string	-
messages[].tool_calls[].type	string	-
messages[].tool_calls[].function	object	-
messages[].tool_call_id	string	p p-0 Tool call ID (for tool role messages)
messages[].reasoning_content	string	p p-0 Reasoning content
temperature	number	p p-0 Sampling temperature
top_p	number	p p-0 Top-p sampling parameter
n	integer	p p-0 Number of completions to generate
stream	boolean	p p-0 Whether to stream the response
stream_options	object	-
stream_options.include_usage	boolean	-
stop	string | array<string>	p p-0 Stop sequences
max_tokens	integer	p p-0 Maximum tokens to generate
max_completion_tokens	integer	p p-0 Maximum completion tokens
presence_penalty	number	-
frequency_penalty	number	-
logit_bias	object	-
logit_bias.[key: string]	number	-
user	string	-
tools	array<object>	-
tools[].type	string	-
tools[].function	object	-
tools[].function.name	string	-
tools[].function.description	string	-
tools[].function.parameters	object	p p-0 Parameter definitions in JSON Schema format
tool_choice	string | object	-
response_format	object	-
response_format.type	string	-
response_format.json_schema	object	p p-0 JSON Schema definition
seed	integer	-
reasoning_effort	string	p p-0 Reasoning effort (for models that support reasoning)
modalities	array<string>	-
audio	object	-
audio.voice	string	-
audio.format	string	-