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 3.8 Flash Lite TTS$6.50
ByteDance/Seed-2.0-pro$3.50

Lowest bill: ByteDance/Seed-2.0-pro · $3.50

Add another

Search by name, then add up to four.

Google: Gemini 3.8 Flash Lite TTSByteDance/Seed-2.0-pro
ProviderGoogleDeepInfra
Modalitytext, audiotext, image
Context33K256K
Input$0.5/1M$0.5/1M
Output$6/1M$3/1M
Cache readNot published—$0.1/1M