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.

Claude Sonnet 4.5$18.00
Anthropic: Claude Sonnet 4.5$18.00

Lowest bill: Claude Sonnet 4.5 · $18.00

Add another

Search by name, then add up to four.

Claude Sonnet 4.5Anthropic: Claude Sonnet 4.5
ProviderNEAR AIAnthropic
Modalitytext, imagetext, image
Context200K1M
Input$3/1M$3/1M
Output$15/1M$15/1M
Cache read$0.3/1M$0.3/1M
Cache writeNot published—$3.75/1M
1-hour cache writeNot published—$6/1M
Tiers and extras
Claude Sonnet 4.5
—
Anthropic: Claude Sonnet 4.5
Web search: $0.01 per request; Above 200,000 prompt tokens: in $6 · out $22.5 · cache read $0.6 · cache write $7.5 · 1h cache write $12