Endpoints
Run Inference
Use POST to run any open source model. This will automatically create an auto-scaling cluster of the model and run inference on that cluster.
POST
Authorizations
Provide your API key as Key your-key-here
in the Authorization
header.
Path Parameters
The specific open source model to run (e.g., gpt2
).
Body
application/json
Send input text and parameters to the model.
Input text to be processed by the model.
Enable or disable streaming responses.
Response
200 - application/json
Successful response from the model.
The model's output.