Observed arrival · 2026-09-13
TokenMercato, an order book for LLM inference
A live marketplace where buyers bid for inference tokens and GPU owners sell idle serving capacity.
○Open
⊠Login
$Paid
†Ads
✦Pretty
●Pro
◎Niche
◉Human
⚑Risk
ƒJS
Field notes
TokenMercato exposes model-specific market prices alongside hosted prices and listed throughput, including Qwen2.5 0.5B at $0.030 and Qwen3 14B at $0.375 per million output tokens. Its stated matching sequence is explicit: a buyer sets a ceiling, the cheapest eligible ask fills, and unused funds return after metered output is settled. The provider workflow calls for one node download and an outbound connection rather than port forwarding.
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
ƒJavaScriptBrowser-side code central
One card from the complete issue