SprinkleAI Reference
The SprinkleAI API follows the widely-adopted Chat Completions wire format. If your SDK accepts a base_url, point it at https://sprinkai.com/v1.
Authentication
All requests require a bearer token obtained after Pro purchase.
Authorization: Bearer sk-spk-XXXXXXXXXXXXXXXX
POST /v1/chat/completions
curl https://sprinkai.com/v1/chat/completions \
-H "Authorization: Bearer sk-spk-..." \
-H "Content-Type: application/json" \
-d '{
"model": "spk-pro",
"messages": [
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"}
]
}'
GET /v1/models
Returns the list of models available to your token.
{
"object": "list",
"data": [
{"id": "spk-small", "object": "model", "owned_by": "sprinkleai"},
{"id": "spk-pro", "object": "model", "owned_by": "sprinkleai"},
{"id": "spk-ultra", "object": "model", "owned_by": "sprinkleai"}
]
}
GET /v1/usage
Inspect remaining quota and request counters for the current billing window.
Rate Limits
| Plan | RPM | Concurrency |
|---|---|---|
| Free | 5 | 1 |
| Pro | 200 | 10 |
| Team | Custom | Custom |
Error Codes
| Code | Meaning |
|---|---|
| 401 | Invalid or missing bearer token |
| 400 | Malformed request / unknown model |
| 429 | Rate limit exceeded |
| 502 | Upstream model unavailable (auto-retry) |