Build with the Aster API.
The API is HTTP/JSON and compatible with common OpenAI-style clients. API access is invite-only during the preview.
Base URL
https://api.fxxk.fun/v1
All endpoints require TLS. The models endpoint is public; generation endpoints require a valid API key and return 401 without one.
Authentication
Pass your API key as a bearer token:
Authorization: Bearer $ASTER_API_KEY
Keys are scoped to a workspace. Do not expose keys in client-side code; call the API from your backend.
List models
GET /v1/models
curl https://api.fxxk.fun/v1/models \
-H "Authorization: Bearer $ASTER_API_KEY"
Returns the public model catalog. The Authorization header is optional for this endpoint.
Chat completions
POST /v1/chat/completions
curl https://api.fxxk.fun/v1/chat/completions \
-H "Authorization: Bearer $ASTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "aster-3.5",
"messages": [
{"role": "system", "content": "You are a concise technical assistant."},
{"role": "user", "content": "Explain vector clocks in two paragraphs."}
],
"temperature": 0.2,
"max_tokens": 512
}'
Set "stream": true to receive server-sent events. The final event includes token usage.
Streaming
Streaming responses use text/event-stream. Each event contains a JSON delta:
data: {"id":"chatcmpl_01H...","object":"chat.completion.chunk","choices":[{"delta":{"content":"A vector"}}]}
data: {"id":"chatcmpl_01H...","object":"chat.completion.chunk","choices":[{"delta":{"content":" clock"}}]}
data: [DONE]
Close the connection to cancel a request. Cancelled requests may still be billed for generated tokens.
Errors
Errors use a consistent JSON shape:
{
"error": {
"message": "Invalid API key provided.",
"type": "invalid_request_error",
"param": null,
"code": "invalid_api_key"
}
}
| Status | Code | Meaning |
|---|---|---|
| 400 | invalid_request | Malformed JSON or missing required field |
| 401 | invalid_api_key | Missing, revoked, or invalid key |
| 403 | access_denied | Workspace does not have access to this model |
| 429 | rate_limit_exceeded | Too many requests; retry with backoff |
| 500 | server_error | Unexpected error; include the request ID |
Rate limits
- Sandbox: 60 requests per minute, 1M tokens per month.
- Scale: 600 requests per minute, usage-based token limits.
- Enterprise: dedicated limits; contact sales.
Every response includes an x-request-id header. Include it when contacting support.
Status
Current platform status and incident history are available on the status page.