Observed arrival · 2026-11-02
Idemcore: signed receipts for reproducible LLM inference
An OpenAI-compatible inference API that says it returns signed receipts so users can verify outputs across hardware.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
- For
- Teams needing reproducible, verifiable LLM outputs
- Worth noticing
- The homepage reports 16 of 16 H100 prompts matched across solo and batched runs, while noting competing engines have higher throughput.
Field notes
The quickstart describes creating a console key, changing the base URL in an OpenAI SDK or using the linked Python and JavaScript SDKs, then checking a signed receipt. The page specifies greedy decoding with temperature omitted or set to zero and n set to one. Its benchmark section reports stable per-token latency on an A10 and matching outputs across batched H100 requests, but says other engines currently achieve higher throughput.
Observed signals
Read the marks
Editorial observations of this landing page, not a rating.
○OpenPublic substance visible
⊠LoginAccess appeared gated
$PaidCommerce or pricing visible
✦PrettyNotable craft visible
●ProPolished or operationally mature
◎NicheUnusually specific use
One card from the complete issue