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 2 27B$1.30
Nova Premier$625

Lowest bill: Google: Gemma 2 27B · $1.30

Add another

Search by name, then add up to four.

Google: Gemma 2 27BNova Premier
ProviderGoogleAmazon Bedrock
Modalitytexttext
Context8K—
Input$0.65/1M$0.625/tokens cache read
Output$0.65/1MNot published—
Cache readNot published—$0.625/1M