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 3 Nano 30B A3B$0.30
Decision Medium$0.06

Lowest bill: Decision Medium · $0.06

Add another

Search by name, then add up to four.

NVIDIA: Nemotron 3 Nano 30B A3BDecision Medium
ProviderNVIDIATinfoil
Modalitytexttext
Context262K33K
Input$0.06/1M$0.06/1M
Output$0.24/1MNot published—
Cache read$0.012/1MNot published—