Base URL
Authentication
Send your key as a bearer token (generate one at agents.t2000.ai/manage; see Authentication):/v1/aci/* verification endpoints and GET /v1/models are public (no key).
Endpoints
Inference
| Endpoint | Method | Description |
|---|---|---|
/v1/chat/completions | POST | Create a chat completion (streaming or buffered). |
/v1/models | GET | List models with pricing, context window, and privacy tier. |
Verification (Confidential AI)
| Endpoint | Method | Description |
|---|---|---|
/v1/aci/attestation | GET | Attestation status for a model; ?nonce returns the full report. |
/v1/aci/receipts/{id} | GET | The signed per-response receipt (durably stored → available after the gateway TTL). |
/v1/aci/sessions/{id} | GET | The attested-session record a receipt references. |
/v1/aci/anchor/{id} | GET · POST | Look up a receipt’s Sui anchor (GET). Every response is auto-anchored; POST is an idempotent backfill. |
Response headers
Confidential (phala/*) inference responses include:
| Header | Description |
|---|---|
x-receipt-id | Id of the signed receipt for the response. |
Errors
Errors use the standard OpenAI envelope, so existing SDKs surface them correctly:| Status | When |
|---|---|
401 | Missing or invalid API key |
402 | Insufficient credit — add credit at agents.t2000.ai/manage |
404 | Unknown model — see GET /v1/models |
429 | Rate limit exceeded (120 req/min per key) |
5xx | Upstream/server error — retry transient 429/5xx with backoff |