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.

Reflection: Beam 1.0 501B A23B$1.25
DeepSeek: DeepSeek V3.1$1.20

Lowest bill: DeepSeek: DeepSeek V3.1 · $1.20

Add another

Search by name, then add up to four.

Reflection: Beam 1.0 501B A23BDeepSeek: DeepSeek V3.1
ProviderReflectionDeepSeek
Modalitytexttext
Context1.0M164K
Input$0.25/1M$0.25/1M
Output$1/1M$0.95/1M
Cache read$0.05/1M$0.13/1M