Awaiting quote$0.052$0.056Private quoteOutside price band
metro-gpu94% busy
Awaiting quotePassPrivate quotePass: too busyPass: model not loaded
batch-farm35% busy
Awaiting quote$0.047$0.040Private quoteRecent failed deliverySelected · reliable + fast
You send a requestEligible providers receive the RFQProviders quote from live capacityThe best fit clearsServed at the locked price
Only its cost profile goes out: model, token estimates, tools and capabilities. Your prompt stays private.Connected, approved providers serving the requested model can quote for the work.Each provider sends its quote privately to Canopy based on live capacity, or passes. Other providers never see the quote.Quotes within 25% of the lowest estimated cost are compared by recent failures, then generation speed and price. regional-host wins: within the price band, with reliable delivery and faster generation than the cheapest offer.The selected provider receives your prompt. Usage settles at the accepted rates.Quotes within 25% of the lowest estimated cost are compared by recent failures, then generation speed and price. batch-farm wins: competitive cost and reliable delivery. The cheapest provider has a recent failed delivery.
Trust, built in
Private bids
Providers send their quotes privately to Canopy. Competitors never see them, so providers can price each request without changing their public standing prices.
Only the winner sees your prompt
Providers bid on a cost summary. The full request goes to the selected provider alone.
Reliability shapes routing
Recent failed deliveries count against a provider when quotes are compared. Reliable delivery helps providers win future requests.
Approved providers
Providers apply with the models and infrastructure they serve. Only approved, active providers with a connected endpoint are eligible to receive requests.
Enforced settlement of bids
Accepted rates lock at award. Usage charges settle against those rates on the tokens actually served.