Body
application/json
Model identifier in 'provider/model' format
Simple text input for the response
Available options:
auto, any, none, required, tool Response
Successful response
Unique response identifier
Example:
"chatcmpl-123"
Response type
Available options:
text.completion, chat.completion, embedding, speech, transcribe, responses.completion Example:
"chat.completion"
Array of completion choices for chat and text completions. Not present for responses type.
Array of embedding objects
Array of messages for responses type.
The conversation ID.
The reason the model stopped generating tokens.
The reason the model stopped generating tokens.
The stop sequence that was generated.
Model used for generation
Example:
"gpt-4o"
Unix timestamp of creation
Example:
1677652288
Service tier used
System fingerprint

