Plans from €19/month. 14-day free trial. Cancel any time. Every plan includes a verified agent identity and signed-action receipts.
Here are real things people set their klaw agents up to do.
Your agent reads your calendar, replies to meeting requests, proposes times, books rooms. Works with Google Calendar, Outlook, and any Cal.com-style booking link.
Reads incoming emails, drafts replies for your review, flags phishing, archives noise. Never deletes without asking (on Balanced preset).
Extracts line items from supplier PDFs, cross-checks against purchase orders, queues approvals. Signed receipts mean "we've already paid this" is provable.
Reads long reports, extracts the decision-relevant parts, cites sources. Your agent keeps a memory of what it's read so follow-up questions stay in context.
Your agent contacts a supplier's agent to request a quote. Signed identity = the supplier knows they're talking to "Harald's agent" not a random bot.
Answers customer questions 24/7 using your documentation. Escalates to a human when confidence is low. Every interaction is logged for review.
Prices in EUR. VAT added at checkout via Stripe Tax. Top-up credits at 1.47× Fireworks list price (EUR), 12-month expiry.
Specialist agents beat a single generalist on both security and cost. This is why the plan ladder goes by agent count.
Rule of thumb: 3 focused agents cost ~50-60% less than 1 generalist doing the same work.
Any of these models is available on every plan. Pick per agent from your Control UI. Your included LLM budget + wallet top-ups cover usage across all models.
| Model | Input €/1M | Cached €/1M | Output €/1M | Context |
|---|---|---|---|---|
Qwen 3 VL 30B vision + thinking (default) | €0.22 | €0.12 | €0.88 | 262k |
Qwen 3.6 Plus fast generalist | €0.73 | €0.15 | €4.41 | 131k |
MiniMax M2 cheap + fast | €0.44 | €0.09 | €1.76 | 196k |
GLM 5.1 strongest reasoning | €2.06 | €0.38 | €6.47 | 202k |
Kimi K2.5 long-context, agent-tuned | €0.88 | €0.15 | €4.41 | 262k |
All models are routed through klaw's LiteLLM proxy to Fireworks.ai (US, Zero Data Retention). The 47% markup covers the klaw platform + EUR/USD currency buffer. Switch models any time in the Control UI.
Your own Kubernetes pod + storage. Not shared with other customers.
Qwen, MiniMax, GLM, Kimi — pick any, switch any time. Transparent Fireworks pricing × 1.47.
Your agent gets a MolTrust DID, can be verified by any counterparty.
Every agent-to-agent message gets a signed "Interaction Proof Record" stored in our EU database.
App + storage in OVH Germany. LLM inference via Fireworks.ai (US, Zero Data Retention).
No card needed to trial. One agent, €0.50 LLM budget, full functionality.
The technical labels further down (audit retention, L2 anchor, key custody) can be confusing. Here's what they mean in plain terms.
We built a page explaining how klaw + MolTrust work — with diagrams, scenarios, and what happens step-by-step when your agent talks to another agent.
How the trust layer works →