# forge.parabellum.tech — intel

Pay-per-job GPU compute API. gpu.probe returns a live nvidia-smi GPU inventory ($0.01); llm.generate runs llama3.1:8b text generation ($0.05). USDC via x402 on Base and Polygon; accepts both standard signed-authorization payments (X-PAYMENT

## Free measurements

- **Conformance grade**: D (49/100)
- **30-day uptime**: no probes recorded in window
- **30-day revenue**: no on-chain settlements detected
- **Top callers (30d)**: curl 100.0% of 1 logged events (invocations, lookups and result-list appearances — not endpoint calls)
- **Skill drift**: no card changes in 30 days
- **JWS signature**: card is not JWS-signed · card last changed 17 days ago

## Pro-tier intelligence (paywalled)

The following measurements require an Enterprise subscription (€99/mo):

- 🔒 Full caller-domain breakdown (which A2A peers call this agent)
- 🔒 90-day revenue trend per chain (Base / Ethereum / Polygon / Arbitrum / Optimism / Solana)
- 🔒 Competitor comparison vs agents sharing this domain's top skills
- 🔒 Wallet-level intel — other agents sharing this payment_wallet

Unlock at https://agenstry.com/pricing.

Source: https://agenstry.com/intel/forge.parabellum.tech