Tencent Cloud (TokenHub)

Tencent Cloud TokenHub setup for Hy3 preview

Tencent Cloud ships as a bundled provider plugin in OpenClaw. It gives access to Tencent Hy3 preview through the TokenHub endpoint (tencent-tokenhub) using an OpenAI-compatible API.

PropertyValue
Provider idtencent-tokenhub
Pluginbundled, enabledByDefault: true
Auth env varTOKENHUB_API_KEY
Onboarding flag--auth-choice tokenhub-api-key
Direct CLI flag--tokenhub-api-key <key>
APIOpenAI-compatible (openai-completions)
Default base URLhttps://tokenhub.tencentmaas.com/v1
Global base URLhttps://tokenhub-intl.tencentmaas.com/v1 (override)
Default modeltencent-tokenhub/hy3-preview

Quick start

Create an API key in Tencent Cloud TokenHub. If you choose a limited access scope for the key, include **Hy3 preview** in the allowed models. 
openclaw onboard --auth-choice tokenhub-api-key

openclaw onboard --non-interactive \
  --auth-choice tokenhub-api-key \
  --tokenhub-api-key "$TOKENHUB_API_KEY"

export TOKENHUB_API_KEY=...

</CodeGroup>
```bash openclaw models list --provider tencent-tokenhub ```

Non-interactive setup

openclaw onboard --non-interactive \
  --mode local \
  --auth-choice tokenhub-api-key \
  --tokenhub-api-key "$TOKENHUB_API_KEY" \
  --skip-health \
  --accept-risk

Built-in catalog

Model refNameInputContextMax outputNotes
tencent-tokenhub/hy3-previewHy3 preview (TokenHub)text256,00064,000Default; reasoning-enabled

Hy3 preview is Tencent Hunyuan's large MoE language model for reasoning, long-context instruction following, code, and agent workflows. Tencent's OpenAI-compatible examples use hy3-preview as the model id and support standard chat-completions tool calling plus reasoning_effort.

The model id is `hy3-preview`. Do not confuse it with Tencent's `HY-3D-*` models, which are 3D generation APIs and are not the OpenClaw chat model configured by this provider.

Tiered pricing

The bundled catalog ships tiered cost metadata that scales with input window length, so cost estimates are populated without manual overrides.

Input tokens rangeInput rateOutput rateCache read
0 - 16,0000.1760.5870.059
16,000 - 32,0000.2350.9390.088
32,000+0.2931.1730.117

Rates are per million tokens in USD as advertised by Tencent. Override pricing under models.providers.tencent-tokenhub only when you need a different surface.

Advanced configuration

OpenClaw defaults to Tencent Cloud's `https://tokenhub.tencentmaas.com/v1` endpoint. Tencent also documents an international TokenHub endpoint: 
```bash
openclaw config set models.providers.tencent-tokenhub.baseUrl "https://tokenhub-intl.tencentmaas.com/v1"
```

Only override the endpoint when your TokenHub account or region requires it.
If the Gateway runs as a managed service (launchd, systemd, Docker), `TOKENHUB_API_KEY` must be visible to that process. Set it in `~/.openclaw/.env` or via `env.shellEnv` so launchd, systemd, or Docker exec environments can read it. 
<Warning>
  Keys set only in `~/.profile` are not visible to managed gateway processes. Use the env file or config seam for persistent availability.
</Warning>
Choosing providers, model refs, and failover behavior. Full config schema including provider settings. Tencent Cloud's TokenHub product page. Tencent Hunyuan Hy3 preview details and benchmarks.