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.

gpt 5 pro inp dzone$16.50
Anthropic: Claude Opus 4.1 (batch)$45.00

Lowest bill: gpt 5 pro inp dzone · $16.50

Add another

Search by name, then add up to four.

gpt 5 pro inp dzoneAnthropic: Claude Opus 4.1 (batch)
ProviderAzureAnthropic
Modalitytextimage, text
Context—200K
Input$16.5/1M$7.5/1M
OutputNot published—$37.5/1M
Cache readNot published—$0.75/1M
Cache writeNot published—$9.375/1M
1-hour cache writeNot published—$15/1M
Tiers and extras
gpt 5 pro inp dzone
—
Anthropic: Claude Opus 4.1 (batch)
Web search: $0.01 per request