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.

Macaron V1 Venti$3.30
DeepSeek: DeepSeek V4 Pro 0423$2.45

Lowest bill: DeepSeek: DeepSeek V4 Pro 0423 · $2.45

Add another

Search by name, then add up to four.

Macaron V1 VentiDeepSeek: DeepSeek V4 Pro 0423
ProviderNovitaDeepSeek
Modalitytexttext
Context1.0M1.0M
Input$0.825/1M$0.8162/1M
Output$2.475/1M$1.632/1M
Cache read$0.165/1M$0.068/1M