Authorizations
Bearer authentication header of the form Bearer <token>
, where <token>
is your auth token.
Body
Use 'full' for end-to-end inference of a prompt.
full
"full"
Conversation history. Required when mode is 'full'.
[
{
"role": "user",
"content": "Write a blog post about Florence."
}
]
ID of the fine-tuned model to use.
"ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1"
Options specific to 'full' mode.
Whether to stream the response.
false
Level of humanization to apply. 0 is none, 1 is low, and 4 is highest.
0 <= x <= 4
4
Sampling temperature, between 0 and 2. Higher values make output more random. 0 is recommended for most use cases.
0
Whether to include quality metrics in the response.
false
Whether to include rouge score in quality metrics. Only applies when include_quality is true.
false
Whether to include original text for comparison to styled text.
false
Whether to include distance metrics comparing the original and styled text.
false
When set to true, headings are not rewritten.
false
Response
A chat completion object.
ID of the chat completion.
"chatcmpl-123"
Type of the object, always 'chat.completion'.
"chat.completion"
Unix timestamp for when the completion was created.
1677652288
Model used for the completion.
"ftm-custom-name-0b5ace7e-ffb2-43cf-8a4d-0af17bc2b1d1"