xAI · Released Mar 28, 2026
Grok 4.6 (high)
xAI's flagship powerhouse model trained on Colossus cluster with real-time knowledge grounding and strong math capabilities.
OpenRating Index
60.8
0–100 composite
Reasoning Index
83.6
0–100 composite
Cost / Task
$0.84
benchmark run
Output speed
69 tok/s
blended tok/s
Time to first token
0.8s
median latency
Input price
$1.8
per 1M tokens
Output price
$9
per 1M tokens
Context window
256K
tokens
Strengths
Real-time knowledge synthesis and live data querying
High performance on competitive programming benchmarks
Extensive reasoning depth with structured code generation
How we rate Grok 4.6 (high)
OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.
OpenRating Index
60.8
Reasoning Index
83.6
Token Pricing
Input per 1M tokens
$1.8
Output per 1M tokens
$9
Cost of 1M input + 1M output
$11
Task Cost Economics
Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.84 total).
Related models
Compare Grok 4.6 (high) with the models it is most often measured against.