Access your endpoints via REST API. All AI endpoints are public and don't require authentication.
Execute Endpoint
Executes the endpoint and returns the LLM response with usage metrics.
GET /api/v1/ai/:orgPath/:projectName/:endpointName
POST /api/v1/ai/:orgPath/:projectName/:endpointName
Get Prompt Only
Returns the generated prompt without calling the LLM. Useful for debugging.
GET /api/v1/ai/:orgPath/:projectName/:endpointName/prompt
POST /api/v1/ai/:orgPath/:projectName/:endpointName/prompt
Response Format
Successful responses include the LLM output and usage statistics:
outputThe structured response from the LLM matching your output schema
usage.tokens_inputNumber of input tokens used
usage.tokens_outputNumber of output tokens generated
usage.latency_msRequest latency in milliseconds
usage.estimated_cost_centsEstimated cost in cents
Example Request
curl -X POST https://api.shapeshyft.ai/api/v1/ai/my-org/my-project/classify \
-H "Content-Type: application/json" \
-d '{"text": "This is a great product!"}'Example Response
{
"success": true,
"data": {
"output": {
"sentiment": "positive",
"confidence": 0.95
},
"usage": {
"tokens_input": 42,
"tokens_output": 15,
"latency_ms": 523,
"estimated_cost_cents": 1
}
}
}