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.

Hermes 2 Pro Llama 3 8B$0.28
MiMo V2.5$0.42

Lowest bill: Hermes 2 Pro Llama 3 8B · $0.28

Add another

Search by name, then add up to four.

Hermes 2 Pro Llama 3 8BMiMo V2.5
ProviderNovitaAtlasCloud
Modalitytexttext
Context8K1.0M
Input$0.14/1M$0.14/1M
Output$0.14/1M$0.28/1M
Cache readNot published—$0.0028/1M