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.

OpenAI: GPT-4o$12.50
Anthropic: Claude Opus 4.8 (batch)$15.00

Lowest bill: OpenAI: GPT-4o · $12.50

Add another

Search by name, then add up to four.

OpenAI: GPT-4oAnthropic: Claude Opus 4.8 (batch)
ProviderPhalaAnthropic
Modalitytext, imagetext, image
Context128K1M
Input$2.5/1M$2.5/1M
Output$10/1M$12.5/1M
Cache readNot published—$0.25/1M
Cache writeNot published—$3.125/1M
1-hour cache writeNot published—$5/1M
Tiers and extras
OpenAI: GPT-4o
—
Anthropic: Claude Opus 4.8 (batch)
Web search: $0.01 per request