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 2 (Gemini 3.1 Flash Image Preview)$3.50
Anthropic: Claude Haiku 4.5 (batch)$3.00

Lowest bill: Anthropic: Claude Haiku 4.5 (batch) · $3.00

Add another

Search by name, then add up to four.

Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)Anthropic: Claude Haiku 4.5 (batch)
ProviderGoogleAnthropic
Modalityimage, texttext, image
Context66K200K
Input$0.5/1M$0.5/1M
Output$3/1M$2.5/1M
Cache readNot published—$0.05/1M
Cache writeNot published—$0.625/1M
1-hour cache writeNot published—$1/1M
Tiers and extras
Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)
Web search: $0.014 per request; Image output: $60 per 1M tokens
Anthropic: Claude Haiku 4.5 (batch)
Web search: $0.01 per request