Autoscaler
Endpoints
Route
5 min
the /route/ endpoint calls on the autoscaler to retrieve a gpu instance address within your {{endpoint}} https //run vast ai/route/ inputs endpoint (string) name of the endpoint api key (string) the vast api key associated with the account that controls the endpoint cost (float) the estimated compute resources for the request the units of this cost are defined by the {{pyworker}} { "endpoint" "your endpoint name", "api key" "your vast api key", "cost" 242 0 } outputs on successful worker return url (string) the address of the worker instance to send the request to reqnum (int) the request number corresponding to this worker instance note that workers expect to receive requests in approximately the same order as these reqnums , but some flexibility is allowed due to potential out of order requests caused by concurrency or small delays on the proxy server signature (string) the signature is a cryptographic string that authenticates the url, cost, and reqnum fields in the response, proving they originated from the server clients can use this signature, along with the server's public key, to verify that these specific details have not been tampered with endpoint (string) same as the input parameter cost (float) same as the input parameter request id (string) the request id is a unique string identifier generated by the server for each individual api request it receives this id is created at the start of processing the request and included in the response, allowing for distinct tracking and logging of every transaction { "endpoint" "your endpoint name", "url" "http //192 168 1 10 8000", "cost" 242 0, "reqnum" 12345, "signature" "a1b2c3d4e5f60708090a0b0c0d0e0f101112131415161718191a1b1c1d1e1f202122232425262728292a2b2c2d2e2f303132333435363738393a3b3c3d3e3f40", " request id" "xxxxxxxx xxxx xxxx xxxx xxxxxxxxxxxx" } on failure to find ready worker endpoint same as the input parameter to /route/ status the breakdown of workers in your endpoint group by status