You can use cURL or any other http client to run inferences:
curl -X POST \
-d '{"input": {"inputs": "..."}}' \
-H 'Content-Type: application/json' \
-H "Authorization: bearer $DEEPINFRA_TOKEN" \
'https://api.deepinfra.com/v1/inference/openai/clip-features'
The inpu/output is compatible with the cog interface.
inputs
stringNewline-separated inputs. Can either be strings of text or image URIs starting with http[s]://
Default value: "a\nb"