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-5.6 Sol Pro$24.00
anthropic/claude-opus-5-5$24.00

Lowest bill: OpenAI: GPT-5.6 Sol Pro · $24.00

Add another

Search by name, then add up to four.

OpenAI: GPT-5.6 Sol Proanthropic/claude-opus-5-5
ProviderOpenAIDeepInfra
Modalitytext, imagetext, image
Context1.1M1M
Input$4/1M$4/1M
Output$20/1M$20/1M
Cache read$0.4/1M$0.2/1M
Cache write$5/1MNot published—
Tiers and extras
OpenAI: GPT-5.6 Sol Pro
Web search: $0.01 per request; Above 272,000 prompt tokens: in $8 · out $30 · cache read $0.8 · cache write $10
anthropic/claude-opus-5-5
—