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: Nano Banana (Gemini 2.5 Flash Image)$2.80
DeepSeek V4.1 Flash$1.50

Lowest bill: DeepSeek V4.1 Flash · $1.50

Add another

Search by name, then add up to four.

Google: Nano Banana (Gemini 2.5 Flash Image)DeepSeek V4.1 Flash
ProviderGoogleNEAR AI
Modalityimage, texttext, image
Context33K1.0M
Input$0.3/1M$0.3/1M
Output$2.5/1M$1.2/1M
Cache read$0.03/1M$0.006/1M
Cache write$0.0833/1MNot published—
Tiers and extras
Google: Nano Banana (Gemini 2.5 Flash Image)
Web search: $0.014 per request; Image input: $0.3 per 1M tokens; Image output: $30 per 1M tokens; Audio: $1 per 1M tokens; Audio cache: $0.1 per 1M tokens; Reasoning: $2.5 per 1M tokens
DeepSeek V4.1 Flash
—