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.

Llama 3 70B Euryale V2.1$2.96
DeepSeek: DeepSeek V4 Pro$4.41

Lowest bill: Llama 3 70B Euryale V2.1 · $2.96

Add another

Search by name, then add up to four.

Llama 3 70B Euryale V2.1DeepSeek: DeepSeek V4 Pro
ProviderNovitaIo Net
Modalitytexttext
Context8K1.0M
Input$1.48/1M$1.49/1M
Output$1.48/1M$2.922/1M
Cache readNot published—$0.745/1M