> ## 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.

# Models

> The t2000 model catalog — open, frontier, and confidential — behind one key, billed per token from one balance. Curated, not a 250-model dump.

`GET /v1/models` returns the live catalog: per-model pricing (the charged rate), context window, and a `privacy` field. The endpoint is **public** — fetch it without a key to browse.

```bash theme={null}
curl https://api.t2000.ai/v1/models
```

***

## The catalog

The launch set is curated — the models developers actually run agents on, plus the frontier set for completeness:

| Tier                       | Models                                                                                                                                                                                     |
| -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **Open**                   | `zai/glm-5.2` · `deepseek/deepseek-v3.2` · `moonshotai/kimi-k2.5` · `alibaba/qwen3-max` · `openai/gpt-oss-120b`                                                                            |
| **Frontier**               | `anthropic/claude-sonnet-5` · `anthropic/claude-opus-4.8` · `openai/gpt-5.5` · `google/gemini-3.1-pro-preview` · `xai/grok-4.3`                                                            |
| **Confidential** (GPU-TEE) | `phala/glm-5.2` · `phala/kimi-k2.6` · `phala/deepseek-v4-flash` · `phala/qwen3.6-27b` · `phala/llama-3.3-70b` · `phala/gpt-oss-120b` · `phala/uncensored-24b` · `phala/qwen3.6-uncensored` |

The live set is always whatever `GET /v1/models` returns — it intersects this curated list with each backend's live catalog. List from the CLI with `t2 models`.

<Note>
  **Reasoning vs fast models.** `glm-5.2` and `kimi-k2.6` are **reasoning** models — they generate a hidden reasoning trace before answering, so they're deeper but noticeably slower (higher latency, more tokens). They carry `"reasoning": true` in `GET /v1/models` (and a `reasoning` tag in `t2 models`). For snappy responses, reach for a non-reasoning model like `gpt-oss-120b`, `deepseek-v4-flash`, or `qwen3.6-27b`. We never cap `max_tokens` by default — the choice of depth vs speed is yours (pass your own `max_tokens` to bound a call).
</Note>

***

## Privacy tiers

Each model carries a `privacy` field so you can choose your posture programmatically:

* **`private`** (default, every model) — **zero data retention**: providers are contractually bound not to store or train on your prompts.
* **`confidential`** (`phala/*`) — inference runs in a **verified GPU-TEE**, with a signed receipt **auto-anchored on Sui** + durably stored, so you can [verify it yourself](/confidential-ai/verify) any time (CLI or [verify.t2000.ai](https://verify.t2000.ai)). Carries a premium over `private` for the verifiable-privacy guarantee. See [Confidential AI](/confidential-ai/how-it-works).

***

## Pricing

One price per model, billed per token from your credit balance — the same rate shown in `GET /v1/models`. There's no separate price book and no per-provider account: **one key, one balance, every model.** Add credit (card, USDC/USDsui, or an Audric plan) at [agents.t2000.ai/manage](https://agents.t2000.ai/manage) — see [Authentication](/authentication).