> ## Documentation Index
> Fetch the complete documentation index at: https://developers.t2000.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# API reference

> Base URL, authentication, endpoints, response headers, and errors for t2000 Private Inference (OpenAI-compatible).

The t2000 [Private Inference](/private-api) is OpenAI-compatible. Point any OpenAI SDK at the base URL and use your key.

***

## Base URL

```text theme={null}
https://api.t2000.ai/v1
```

***

## Authentication

Send your key as a bearer token (generate one at [agents.t2000.ai/manage](https://agents.t2000.ai/manage); see [Authentication](/authentication)):

```bash theme={null}
Authorization: Bearer $T2000_API_KEY
```

Agents can also call **keyless** over [x402](/agent-payments) (pay-per-call in USDC) via the gateway — no account. The `/v1/aci/*` verification endpoints and `GET /v1/models` are **public** (no key).

***

## Endpoints

### Inference

| Endpoint                                                  | Method | Description                                                 |
| --------------------------------------------------------- | ------ | ----------------------------------------------------------- |
| [`/v1/chat/completions`](/api-reference/chat-completions) | POST   | Create a chat completion (streaming or buffered).           |
| [`/v1/models`](/api-reference/models)                     | GET    | List models with pricing, context window, and privacy tier. |

### Verification ([Confidential AI](/confidential-ai/how-it-works))

| Endpoint                                            | Method     | Description                                                                                            |
| --------------------------------------------------- | ---------- | ------------------------------------------------------------------------------------------------------ |
| [`/v1/aci/attestation`](/api-reference/attestation) | GET        | Attestation status for a model; `?nonce` returns the full report.                                      |
| [`/v1/aci/receipts/{id}`](/api-reference/receipts)  | GET        | The signed per-response receipt (durably stored → available after the gateway TTL).                    |
| [`/v1/aci/sessions/{id}`](/api-reference/sessions)  | GET        | The attested-session record a receipt references.                                                      |
| [`/v1/aci/anchor/{id}`](/api-reference/anchor)      | 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](/api-reference/receipts) for the response. |

***

## Errors

Errors use the standard OpenAI envelope, so existing SDKs surface them correctly:

```json theme={null}
{ "error": { "message": "Invalid API key.", "type": "invalid_request_error", "code": "invalid_api_key", "param": null } }
```

| Status | When                                                                                         |
| ------ | -------------------------------------------------------------------------------------------- |
| `401`  | Missing or invalid API key                                                                   |
| `402`  | Insufficient credit — add credit at [agents.t2000.ai/manage](https://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                             |