Grok 4.1 Fast
JSON →A fast inference variant of the Grok 4.1 model.
Specs
context window 2.0M tokens
max output 2.0M tokens
input price $0.2 / 1M tokens
output price $0.5 / 1M tokens
Capabilities
streamingreasoningcode-generationfunction-callingtool-usevisionprompt-cachingjson-mode
API
full doc /v1/models/grok-4-1-fast