Endpoint · inferencePOSTapi.erb-llm.com /v1/chat/completions
Private, self-hosted LLM inference service for agents: a local open-weight model serving OpenAI-compatible chat completions.
Read more
Private, self-hosted LLM inference service for agents: a local open-weight model serving OpenAI-compatible chat completions. Prompts never leave this machine - use it where data can't go to OpenAI/Anthropic. Pay per call in USDC on Base via x402, no API key or account. Chat tiers by output ceiling (quick 4,096 / long 8,192 / extended 32,768 tokens) plus cheap 768-dim embeddings for RAG and semantic search. Send a messages array, get chat.completion JSON. No wallet? Free trial: POST /v1/trial.Overview
Grade?
UNRATED
0 of 30 paid calls toward a letter
Price
$0.005 per call
Paid calls
none yet
delivery unknown until someone pays
More info
Seller?
URL
https://api.erb-llm.com/v1/chat/completions
Seen
first 25 days ago · last 12 hr ago
21 free handshakes
Payment
Pays through
x402
Offered on?
Base USDC
Listed on?
Base
Handshakescomputed 2 days ago
0.200 from 17 free handshakes over 30 days · UNRATED ?
| Component | Weight | Measured | Lower bound ? | Adds | Short ? | Uncertain ? | |
|---|---|---|---|---|---|---|---|
| livenesscosts the most it answered at all |
0.60 | 0.11 | 0.000 | 0.000 | −0.534 | −0.066 | |
| latency p95 it answered as fast as its class |
0.20 | 0.00 | 0.000 | 0.000 | −0.200 | 0 | |
| price stability the price stayed where it was listed |
0.20 | 1.00 | 1.000 | 0.200 | 0 | 0 | |
| Composite | 1.00 | 0.200 | gap to 1.000 = 0.800 · 0.734 short · 0.066 uncertain | 0.200 | −0.734 | −0.066 |
Not measured: correctness · nobody paid; honesty · nobody paid; schema conformance · no answer had a published shape to check
BURN_INFREE_TIER_ONLY
Verify it yourself
npx teppi-check https://api.erb-llm.com/v1/chat/completionscurl -s https://api.teppi.xyz/v1/trust/cap_01M22B295WFN3R0XK76VYWWB09