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.

NVIDIA Nemotron Nano 2$0.29
Amazon: Nova Lite 1.0$0.30

Lowest bill: NVIDIA Nemotron Nano 2 · $0.29

Add another

Search by name, then add up to four.

NVIDIA Nemotron Nano 2Amazon: Nova Lite 1.0
ProviderAmazon BedrockAmazon
Modalitytexttext, image
Context—300K
Input$0.06/1M$0.06/1M
Output$0.23/1M$0.24/1M