ZeroGPU Router

Cut your OpenClaw agent's inference costs. Route trivial AI tasks — summarize, classify, redact PII, extract JSON, short chat — to small/nano models instead of burning frontier-model tokens.

What it does

Your OpenClaw agent keeps doing the heavy reasoning. Routine tasks get offloaded to ZeroGPU's small models — typically 100–1000× cheaper per call.

• Task-specific skills (summarize, classify-iab, redact-pii, …)
• Each skill shells out to the local zerogpu CLI via the agent's Bash tools — nothing to host or register
• Per-call savings logged with model, latency, and a real savings_usd figure

Quickstart

Get an API key at platform.zerogpu.ai, then:

# 1. Install the CLI the skills shell out to
npm install -g zerogpu-cli

# 2. Log in (prompts for API key)
zerogpu login

# 3. Install the plugin
openclaw plugins install clawhub:zerogpu-router

Pin a release: clawhub:zerogpu-router@2.0.0.

Every skill shells out to the zerogpu CLI — install it globally and run a one-time zerogpu login before using the plugin. In sandboxed/Docker agents, make sure zerogpu is available inside the container.

Try it

Ask your agent in plain language — it picks the right skill, runs the zerogpu CLI locally instead of the host model, and replies with the result plus a savings line. The replies below are illustrative: the models are small, so output is concise and a little mechanical.

Summarize — condense a meeting recap:

summarize this: Team, quick recap of today's sync. We agreed to push the mobile
checkout redesign to the March release because the payments integration slipped a
sprint. QA flagged two blocker bugs on Android that engineering will prioritize
this week. Marketing still wants the new pricing page live before the end of the
quarter, so we will revisit scope on Thursday. Please update your tickets before
standup tomorrow.

Reply:

mobile checkout redesign pushed to march release, payments integration slipped a
sprint. qa flagged two android blocker bugs, engineering to fix this week.
marketing wants pricing page live by end of quarter, scope revisited thursday.
update tickets before standup.

model: llama-3.1-8b-instruct-fast · 78 tokens in / 41 out
💰 ZeroGPU savings so far: ≈ $2 (18,730 frontier-model tokens offloaded)

Classify — triage a support ticket against your own labels:

classify this support ticket as billing, bug, feature-request, or account —
"I was charged twice for my October subscription, and the second charge is a
different amount than my plan. Please refund the duplicate and explain the
difference."

Reply:

[
  { "label": "billing",         "score": 0.94 },
  { "label": "account",         "score": 0.29 },
  { "label": "bug",             "score": 0.07 },
  { "label": "feature-request", "score": 0.02 }
]

model: deberta-v3-small · 61 tokens in
💰 ZeroGPU savings so far: ≈ $2 (19,180 frontier-model tokens offloaded)

Redact PII — scrub a CRM note before sharing it:

redact the PII in this CRM note before I share it with the vendor —
"Call with Daniel Okafor (daniel.okafor@brightwave.io, +1 206-555-0147) on Tue.
Send the enterprise quote to their AP team at 400 Pine St, Seattle, WA 98101.
Card on file ends 4412 — do not reference it in email."

Reply:

Call with [PERSON] ([EMAIL], [PHONE_NUMBER]) on Tue. Send the enterprise quote to
their AP team at [ADDRESS]. Card on file ends 4412 — do not reference it in email.

model: gliner-multi-pii-v1 · 5 spans masked
💰 ZeroGPU savings so far: ≈ $2 (19,650 frontier-model tokens offloaded)

Note the card last-four is left untouched — the PII model covers standard categories (names, emails, phones, addresses), not project-specific identifiers. Strip those yourself.

The skills you get

Every skill returns { <task fields>, model, usage, savings }.

Watch your savings

Live dashboard at platform.zerogpu.ai — token usage, latency, per-tool savings, broken down by agent and time range.

Links

• Website: https://zerogpu.ai
• Dashboard: https://platform.zerogpu.ai
• Source: https://github.com/zerogpu/zerogpu-router
• Full setup guide: https://github.com/zerogpu/zerogpu-router/tree/main/agents/openclaw
• Issues / contact: hello@zerogpu.ai

License

MIT — see LICENSE.