Features
Resources
Pricing
Back to Models
Grok 4 Fast (Non-Reasoning)
Supports text, vision
Input Modalities
text
vision
Features
-
Pricing
Pricing is based on the number of tokens used, or other metrics based on the model type.
Per 1M tokens
Input
$0.20
Output
$0.50
Cached input
$0.05
Specifications
context window
2,000,000
max output tokens
30,000
Latency
3.10s
Throughput
136.90 TPS