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 3.5 Flash$10.50
Anthropic: Claude Sonnet 4.5 (batch)$9.00

Lowest bill: Anthropic: Claude Sonnet 4.5 (batch) · $9.00

Add another

Search by name, then add up to four.

Google: Gemini 3.5 FlashAnthropic: Claude Sonnet 4.5 (batch)
ProviderGoogleAnthropic
Modalitytext, image, video, audiotext, image
Context1.0M1M
Input$1.5/1M$1.5/1M
Output$9/1M$7.5/1M
Cache read$0.15/1M$0.15/1M
Cache write$0.0833/1M$1.875/1M
1-hour cache writeNot published—$3/1M
Tiers and extras
Google: Gemini 3.5 Flash
Web search: $0.014 per request; Image input: $1.5 per 1M tokens; Audio: $3 per 1M tokens; Audio cache: $0.3 per 1M tokens; Reasoning: $9 per 1M tokens
Anthropic: Claude Sonnet 4.5 (batch)
Web search: $0.01 per request; Above 200,000 prompt tokens: in $3 · out $11.25 · cache read $0.3 · cache write $3.75 · 1h cache write $6