Grok 3 Mini Fast

JSON →
xai llm
text

A fast inference variant of the Grok 3 Mini model for low-latency responses.

context window 131K tokens
max output 131K tokens
input price $0.6 / 1M tokens
output price $4 / 1M tokens
streamingcode-generationfunction-callingtool-useprompt-cachingreasoning