VAPI•2y ago

Logs show that GPT 4o, GPT 4 and GPT 3.5 Turbo are launched in parallel. How come?

Curious to unterstand here what is going on : is there a reason ? Any cost related impact ?
Context call : https://dashboard.vapi.ai/calls/d09d3c22-3999-46aa-961a-c96f593c69b4

Capture_decran_2024-06-19_a_16.36.09.png

Vapi•6/19/24, 3:46 PM

Relevant threads

These are relevant threads you might take a look into before continuing further:

@1248729937205133382
@1246156772230692995
@1247553809102798889
@1242213359600930857
@1247559658001137736
@1245224971089870938
@1243287247218937898
@1247072669631905874
@1248295851588063322
@1239719244338430053
@1241519757941805279
@1247531659163598859
@1242315416307761153
@1243295223862526024
@1247600940803035157
@1242914198896382004
@1242795705920258068
@1237415196549714033
@1238603485084254228
@1248603965180870666
@1243971237735305318
@1245889476589256735
@1245483301137940560
@1244783157031735338
@1242844005381832775
@1243307743847383231
@1235090114988736615
@1244035082243539087
@1249307086265782432
@1249324577214169209
@1249356085458898966
@1249608410144571434
@1249794652232614011
@1249812719444561962
@1250092104856768584
@1250156356967727144
@1250213297572024440
@1250563201628635167
@1250824638305402890
@1250867745189527713
@1251230232707338270
@1251233770250567711
@1251579097923195036
@1251581002669887518
@1252309420885545040
@1252657790993043528
@1252659844142596180
@1252898312839757834
@1253001413395742741
@1253010217839493173
@1253011560293601341

Vapi•6/19/24, 3:46 PM

@MaxGdj
It seems like you're inquiring about a specific call and its potential cost-related impact. To provide you with accurate information, I would need to know what specific details you are looking for. Are you interested in the duration of the call, the cost breakdown, or any other specific metrics related to this call? Once I have more context, I can assist you better. If you're looking for general information on how calls are billed or how to manage costs, I can guide you through that as well. Please provide more details so I can assist you accordingly.

Vapi•6/19/24, 3:46 PM

You can continue this conversation by mentioning me in the message.

living-lavender•6/19/24, 6:28 PM

Can you share me the call_id?

primary-violetOP•6/20/24, 9:01 AM

Sure, id in the url: d09d3c22-3999-46aa-961a-c96f593c69b4

living-lavender•6/20/24, 10:57 AM

Basically, these model were requested but it was timeout due to which next model was called

Logs show that GPT 4o, GPT 4 and GPT 3.5 Turbo are launched in parallel. How come?

Similar Threads

Similar Threads

Similar Threads