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.

deepseek-v4-pro$6.30
Anthropic: Claude Sonnet Latest$12.00

Lowest bill: deepseek-v4-pro · $6.30

Add another

Search by name, then add up to four.

deepseek-v4-proAnthropic: Claude Sonnet Latest
ProviderInference.netAnthropic
Modalitytexttext, image
Context1.0M1M
Input$2.1/1M$2/1M
Output$4.2/1M$10/1M
Cache read$0.0036/1M$0.1/1M
Cache writeNot published—$2.5/1M
1-hour cache writeNot published—$4/1M
Tiers and extras
deepseek-v4-pro
—
Anthropic: Claude Sonnet Latest
Web search: $0.01 per request