Text Generation Inference custom API

documented

Custom API for text-generation-inference endpoints (see official API docs for exact paths).

POST /v1/<custom-api-endpoint>Text Generation Inferenceno implementation yet0 runs

Input

custom_api_endpoint*

Custom API endpoint path

generate

inputs*

Input text for generation

max_tokens*

Maximum tokens to generate

temperature

Sampling temperature

top_p

Nucleus sampling probability

do_sample

Use sampling (true/false)

Calls Hugging Face as you (your API key is your account); keychains.dev holds the credentials.