Tencent Cloud TokenHub & TokenPlan Setup

Install the official Tencent Cloud provider plugin to reach Tencent Hy3 via two endpoints, TokenHub (tencent-tokenhub) and TokenPlan (tencent-tokenplan), through an OpenAI-compatible API.

Property	Value
Provider ids	`tencent-tokenhub`, `tencent-tokenplan`
Package	`@openclaw/tencent-provider`
TokenHub auth env var	`TOKENHUB_API_KEY`
TokenPlan auth env var	`TOKENPLAN_API_KEY`
TokenHub onboarding flag	`--auth-choice tokenhub-api-key`
TokenPlan onboarding flag	`--auth-choice tokenplan-api-key`
TokenHub direct CLI flag	`--tokenhub-api-key <key>`
TokenPlan direct CLI flag	`--tokenplan-api-key <key>`
API	OpenAI-compatible (`openai-completions`)
TokenHub base URL	`https://tokenhub.tencentmaas.com/v1`
TokenHub global base URL	`https://tokenhub-intl.tencentmaas.com/v1` (override)
TokenPlan base URL	`https://api.lkeap.cloud.tencent.com/plan/v3`
Default model	`tencent-tokenhub/hy3`

Quick start

Create a Tencent API key

Generate an API key for both Tencent Cloud TokenHub and TokenPlan. When the key's access scope is restricted, add hy3 (and hy3 preview if TokenHub usage is intended) to the permitted models.

Run onboarding

openclaw onboard --auth-choice tokenhub-api-key

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

openclaw onboard --auth-choice tokenplan-api-key

openclaw onboard --non-interactive --accept-risk --skip-health \
  --auth-choice tokenplan-api-key \
  --tokenplan-api-key "$TOKENPLAN_API_KEY"

export TOKENHUB_API_KEY=...
export TOKENPLAN_API_KEY=...

Verify the model

openclaw models list --provider tencent-tokenhub
openclaw models list --provider tencent-tokenplan

Non-interactive setup

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

# TokenPlan
openclaw onboard --non-interactive \
  --mode local \
  --auth-choice tokenplan-api-key \
  --tokenplan-api-key "$TOKENPLAN_API_KEY" \
  --skip-health \
  --accept-risk

Note

--accept-risk must be supplied together with --non-interactive.

Built-in catalog

Model ref	Name	Input	Context	Max output	Notes
`tencent-tokenhub/hy3-preview`	hy3 preview (TokenHub)	text	256,000	128,000	deprecated; use `hy3`
`tencent-tokenhub/hy3`	hy3 (TokenHub)	text	256,000	128,000	reasoning-enabled; current
`tencent-tokenplan/hy3`	hy3 (TokenPlan)	text	256,000	128,000	reasoning-enabled; current

Tencent Hunyuan's hy3 is a large MoE language model built for reasoning, extended-context instruction following, coding, and agent tasks. The OpenAI-compatible examples from Tencent reference hy3 as the model id, with support for standard chat-completions tool calling and reasoning_effort.

Tip

The model id is hy3. It should not be mistaken for Tencent's HY-3D-* models, which are 3D generation APIs and not the OpenClaw chat model this provider configures.

Advanced configuration

Endpoint override

OpenClaw's built-in catalog points to Tencent Cloud's https://tokenhub.tencentmaas.com/v1 endpoint. Only change it when your TokenHub account or region calls for a different one:

openclaw config set models.providers.tencent-tokenhub.baseUrl "https://your-endpoint/v1"

Environment availability for the daemon

For a Gateway running as a managed service (launchd, systemd, Docker), TOKENHUB_API_KEY and TOKENPLAN_API_KEY need to be accessible to that process. Configure them in ~/.openclaw/.env or through env.shellEnv so launchd, systemd, or Docker exec environments can pick them up.

Warning

Keys exported only within an interactive shell stay hidden from managed gateway processes. Rely on the env file or config seam for persistent access.

Model providers, Picking providers, model refs, and failover settings.
Configuration reference, Complete config schema with provider options.
Tencent TokenHub, Tencent Cloud's TokenHub product page.
Hy3 preview model card, Tencent Hunyuan Hy3 preview specs and benchmarks.