theserverless.dev InferenceList

Compare

Add up to four models. The bill starts at 1M input tokens, 1M output tokens, and 1,000 units.

Monthly bill

Token models use the token counts. Other models use units times the flat rate.

PrismML: Ternary Bonsai 2 27B$0.58
Ling 3.0 Flash VL$0.30

Lowest bill: Ling 3.0 Flash VL · $0.30

Add another

Search by name, then add up to four.

PrismML: Ternary Bonsai 2 27BLing 3.0 Flash VL
ProviderPrism MlNovita
Modalitytext, imagetext, image, video
Context262K262K
Input$0.075/1M$0.075/1M
Output$0.5/1M$0.22/1M
Cache read$0.0375/1M$0.015/1M