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.

Gemini 3.8 Flash Developer$4.50
Google: Gemini 3.5 Flash (batch)$5.25

Lowest bill: Gemini 3.8 Flash Developer · $4.50

Add another

Search by name, then add up to four.

Gemini 3.8 Flash DeveloperGoogle: Gemini 3.5 Flash (batch)
ProviderAtlasCloudGoogle
Modalitytext, image, video, audiotext, image, video, audio
Context1.0M1.0M
Input$0.75/1M$0.75/1M
Output$3.75/1M$4.5/1M
Cache read$0.075/1M$0.075/1M
Tiers and extras
Gemini 3.8 Flash Developer
—
Google: Gemini 3.5 Flash (batch)
Web search: $0.014 per request; Image input: $0.75 per 1M tokens; Audio: $1.5 per 1M tokens; Audio cache: $0.15 per 1M tokens; Reasoning: $4.5 per 1M tokens