MONITORED COMPANY
DeepInfra
Public pricing pages, with dated observations and source health.
About DeepInfra
DeepInfra offers cost-effective, scalable, easy-to-deploy, and production-ready machine-learning models and infrastructures for deep-learning models.
Official description · checked 2026-10-08 ↗Pricing plans
7 rates USD listings are shown when no local price is available.
DeepInfra inference models — token pricingUSD listing · usage-based
Contact salesper 1M tokens (model-specific input, cached input, and output rates)
Captured 2026-10-10 · Official price source ↗
Custom LLM — A100USD listing · uptime; billed in minute granularity, invoiced weekly
$0.89per GPU-hour
Captured 2026-10-10 · Official price source ↗
Custom LLM — H100USD listing · uptime; billed in minute granularity, invoiced weekly
$2.20per GPU-hour
Captured 2026-10-10 · Official price source ↗
Custom LLM — H200USD listing · uptime; billed in minute granularity, invoiced weekly
$2.69per GPU-hour
Captured 2026-10-10 · Official price source ↗
Custom LLM — B200USD listing · uptime; billed in minute granularity, invoiced weekly
$3.69per GPU-hour
Captured 2026-10-10 · Official price source ↗
Custom LLM — B300USD listing · uptime; billed in minute granularity, invoiced weekly
$4.89per GPU-hour
Captured 2026-10-10 · Official price source ↗
Dedicated Instances and ClustersUSD listing
Contact sales
Captured 2026-10-10 · Official price source ↗
Dated observations, not live quotes. USD listings are fallbacks where no local rate is available.
Published changes
No published changes yet.
Price history
No reviewed price history yet.