All model prices

grok-4.1-fast-non-reasoning

Vertex AI · grok-4.1-fast-non-reasoning

grok-4.1-fast-non-reasoning from Vertex AI: $0.2 per million input tokens, $0.5 per million output tokens, $0.05 per million cached input tokens.

Prices in US dollars per million units
RatePriceApplies
Input$0.2 per 1M input tokensOrdinary
Cached input$0.05 per 1M cached input tokensOrdinary
Output$0.5 per 1M output tokensOrdinary
Most input tokens
128,000
Most output tokens
128,000