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 Haiku 4.5$6.00
Anthropic: Claude Sonnet 5 (batch)$6.00

Lowest bill: Claude Haiku 4.5 · $6.00

Add another

Search by name, then add up to four.

Claude Haiku 4.5Anthropic: Claude Sonnet 5 (batch)
ProviderNEAR AIAnthropic
Modalitytext, imagetext, image
Context200K1M
Input$1/1M$1/1M
Output$5/1M$5/1M
Cache read$0.1/1M$0.1/1M
Cache writeNot published—$1.25/1M
1-hour cache writeNot published—$2/1M
Tiers and extras
Claude Haiku 4.5
—
Anthropic: Claude Sonnet 5 (batch)
Web search: $0.01 per request