How does Tensor estimate prices for an NFT?


As a NFT junkie, hodler, or trader, knowing roughly how much a particular NFT mint is super important.

We do this implicitly when we go to our favorite marketplace and look at what's listed: we take into account the current floor price, the recent sales transactions, the attributes/traits, and the rarity of the NFT to come up with our magic number.

Another heuristic is to assume all NFTs of a collection is at least the current floor price: but what if you'd like to know the approximate price of non-floor mints?

You could then use these prices to determine the value of collateral in NFT loans (as a lender or borrower), if listings are underpriced/overpriced, or the true value of your NFT portfolio.


Introducing Tensor's NFT price estimates & appraisals. We use state-of-the-art ML/AI models to estimate NFT prices in real-time. We've done this professionally for years in the traditional equity & stock space, and are now applying our data science & modeling know-how to NFT pricing.

We take into account many data points, including (but not limited to) the NFT's traits, rarity, and historical bids, listings & sales transactions from the vast majority of secondary marketplaces.

You can see how our models compare with other price estimators on our performance page:

pageOur Performance

We're constantly refining our models: expect that our performance & accuracy will only improve over time!

Try it out

Check out our REST API endpoint to retrieve both historical and recent estimated prices for the collections we track both on Solana and Ethereum:


Last updated