Grok 4.1 Fast

JSON →
xai llm
text

A fast inference variant of the Grok 4.1 model.

context window 2.0M tokens
max output 2.0M tokens
input price $0.2 / 1M tokens
output price $0.5 / 1M tokens
streamingreasoningcode-generationfunction-callingtool-usevisionprompt-cachingjson-mode
full doc /v1/models/grok-4-1-fast