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.

google.gemma-4-e2b$0.12
DeepSeek OCR$0.12

Lowest bill: google.gemma-4-e2b · $0.12

Add another

Search by name, then add up to four.

google.gemma-4-e2bDeepSeek OCR
ProviderAmazon BedrockAtlasCloud
Modalitytexttext, image
Context—8K
Input$0.04/1M$0.04/1M
Output$0.08/1M$0.08/1M
Cache readNot published—$0.04/1M