Private LLM Inference
POST https://api.erb-llm.com/v1/chat/completions
Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware - your data is never forwarded to OpenAI/Anthropic or any third-party LLM cloud. OpenAI-compatible chat completions: summarize, draft, extract, translate, code, answer questions. Send a messages array, get chat.completion JSON. Pay per call in USDC on Base (x402), no API key or account. Tiers by output cap: quick 4,096 / long 8,192 / extended 32,768 tokens. Free trial: POST /v1/trial.
How to buy
This endpoint takes pay-per-call payments over x402. Call it once without paying to see its live price; any x402 client then pays and retries automatically.
curl -i -X POST "https://api.erb-llm.com/v1/chat/completions"
# HTTP/1.1 402 Payment Required: price, asset and payTo are in the responseRecent checks
| Checked (UTC) | Result | Status | Time | Live price |
|---|---|---|---|---|
| 2026-10-11 12:46 | Valid 402 | 402 | 352 ms | $0.001 |
| 2026-10-11 08:15 | Valid 402 | 402 | 367 ms | $0.001 |
| 2026-10-11 03:45 | Valid 402 | 402 | 399 ms | $0.001 |
| 2026-10-10 23:30 | Valid 402 | 402 | 278 ms | $0.001 |
| 2026-10-10 18:00 | Valid 402 | 402 | 383 ms | $0.001 |
Receipts
No test purchases yet. Graded test purchases are next on our list; until then every number here comes from unpaid checks.
What a check proves