Grok 3 Fast
JSON →The latest fast inference variant of the Grok 3 large language model, optimized for speed.
Specs
context window 131K tokens
max output 131K tokens
input price $5 / 1M tokens
output price $25 / 1M tokens
Capabilities
streamingreasoningcode-generationfunction-callingtool-useprompt-caching
API
full doc /v1/models/grok-3-fast-latest