Grok 3 Mini

JSON →
xai llm
text

A smaller, more efficient variant of the Grok 3 model for faster inference.

context window 131K tokens
max output 131K tokens
input price $0.3 / 1M tokens
output price $0.5 / 1M tokens
streamingcode-generationfunction-callingtool-useprompt-cachingreasoning
full doc /v1/models/grok-3-mini