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: Gemini 3.1 Flash Lite (batch)$0.88
Gemma 4 26B A4B$0.53

Lowest bill: Gemma 4 26B A4B · $0.53

Add another

Search by name, then add up to four.

Google: Gemini 3.1 Flash Lite (batch)Gemma 4 26B A4B
ProviderGoogleNovita
Modalitytext, image, video, audiotext, image
Context1.0M262K
Input$0.125/1M$0.13/1M
Output$0.75/1M$0.4/1M
Cache read$0.0125/1MNot published—
Tiers and extras
Google: Gemini 3.1 Flash Lite (batch)
Web search: $0.014 per request; Image input: $0.125 per 1M tokens; Audio: $0.25 per 1M tokens; Audio cache: $0.025 per 1M tokens; Reasoning: $0.75 per 1M tokens
Gemma 4 26B A4B
—