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 8B Stheno V3.2$0.10
DeepSeek: DeepSeek V4.1 Flash (batch)$0.20

Lowest bill: Llama 3 8B Stheno V3.2 · $0.10

Add another

Search by name, then add up to four.

Llama 3 8B Stheno V3.2DeepSeek: DeepSeek V4.1 Flash (batch)
ProviderNovitaDeepSeek
Modalitytexttext, image
Context8K1.0M
Input$0.05/1M$0.05/1M
Output$0.05/1M$0.15/1M
Cache readNot published—$0.004/1M