Grok 4 Fast
by xAI
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)
Capabilities
Pricing
Input Tokens
Per 1M tokens
Free
Output Tokens
Per 1M tokens
Free
Image Processing
Per 1M tokens
$0.00/1M tokens
Supported Modalities
Input
text
image
Output
text
Performance Benchmarks
Intelligence Index
Overall intelligence score
38.6
Coding Index
Programming capability
28.1
Math Index
Mathematical reasoning
41.3
GPQA
Graduate-level questions
60.6%
MMLU Pro
Multitask language understanding
73.0%
HLE
Human-like evaluation
5.0%
LiveCodeBench
Real-world coding tasks
40.1%
AIME 2025
Advanced mathematics
41.3%
Specifications
- Context Length
- 2.0M tokens
- Provider
- xAI
- Throughput
- 174.639 tokens/s
- Released
- Sep 19, 2025
- Model ID
- x-ai/grok-4-fast
More from xAI
View all modelsCompare Models
Select a model to compare with Grok 4 Fast