Free tier available — 500K tokens/month, no credit card required.See Plans →

FOUR MODELS.
TWO PLATFORMS.

Two GPU models on NVIDIA L40S for paid tiers. Two CPU models on IBM POWER10 free for everyone. Every OpenClaw config slot covered — no gaps, no workarounds.

Qlaw Orchestrator

Starter+

Your agent's brain. Plans, reasons, and acts. Powers OpenClaw's orchestrator pattern, coordinates sub-agents, and executes tool calls. Deep thinking mode for complex tasks, direct mode for fast ones. Native tool calling means agents actually complete work, not just describe it.

Agentstool callingreasoningsub-agent coordination
Speed
⚡⚡⚡
Context
64K
Hardware
Qwen3-32B
API ID
qlaw-orchestrator
Paid Tiers — NVIDIA L40S GPU
🧠
Qlaw Orchestrator
Your agent's brain
Full tool calling · Deep reasoning · 64K context · GPU-fast
Powered by Qwen3-32B on NVIDIA L40S
Starter+
👁
Qlaw Vision
Your agent's eyes
Screenshot analysis · PDF reading · Browser automation · Auto-routed
Powered by Qwen2.5-VL-7B on NVIDIA L40S
Starter+
Free Tier — Power-class servers
💻
Qlaw Coder-Next
Your agent's coder
Tool calling · 100K context · Thinking mode · 80B MoE
Powered by Qwen3-Coder-Next on Power-class servers
Free+
Qlaw Nano
Your agent's reflex
~50 tok/s · 16K context · Unlimited · Tool calling
Powered by Qwen3-1.7B on Power-class servers
Free+
ModelBest ForSpeedContextPlan
Qlaw OrchestratorAgents, tool calling, reasoning, sub-agent coordination⚡⚡⚡64KStarter+
Qlaw VisionScreenshots, PDFs, browser views, document analysis⚡⚡⚡32KStarter+
Qlaw Coder-NextCoding agents, repo analysis, multi-file edits, OpenClaw orchestrator100KFree+
Qlaw NanoRouting, classification, quick summaries, heartbeat agents, structured extraction⚡⚡⚡⚡16KFree+
Model names are role-based and permanent. When the underlying model is upgraded, your config stays the same — only the hardware improves. Paid subscribers vote on all model changes.