Loading...
Loading...
Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)
Quality Index
23.1
162nd of 444
Top 37%
Coding Index
19.0
155th of 354
Top 44%
Math Index
41.3
151st of 268
Top 58%
Price/1M
$0.28
330th cheapest
8% below median
Top 49%
Speed
128 tok/s
Top 19%
TTFT
0.29s
Context Window
2.0M
1st largest
Top 1%
Input
$0.20
per 1M tokens
Output
$0.50
per 1M tokens
Blended
$0.28
per 1M tokens
Cheaper than 51% of models. Median price is $0.30/1M tokens.
Daily
$0.28
Monthly
$8.25
128
tokens/sec
Faster than 81% of models
0.29
seconds
Faster than 59% of models
0.29
seconds
Faster than 60% of models
Market Median
45 tok/s
183% faster
Median TTFT
0.42s
30% faster
Throughput/Dollar
466
tok/s per $/1M
Speed Comparison
Context Window
2.0M
tokens
Larger than 99% of models
Max Output
30K
tokens
2% of context