Grok 4 Fast
GrokBalanced
ThinkingTool UseVisionStructured Output
About this model
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)
Performance Tier
Balanced
Grok 4 Fast is a balanced model from Grok : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plans| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.200 |
| Output (completion) | $0.500 |
| Cache read | $0.050 |
Capabilities
Context Length2.0M
Max Output Tokens30K
TokenizerGrok
Inputtext, image, file
Outputtext
Release DateSeptember 19, 2025
Benchmarks
General Intelligence
MMLU
87.8%
Mathematics
MATH-500
85%
AIME 2025
92%
Programming
HumanEval
90.5%
LiveCodeBench
80%
Reasoning
Humanity's Last Exam
20%
Recommended Use Cases
General ChatCodingCreative WritingSummarization
Strengths
- Fast variant of Grok 4 with most of its capability retained
- Strong coding and math performance at lower latency
- Good for real-time conversational applications
Limitations
- Slightly lower accuracy than full Grok 4
- Less suited for complex multi-step reasoning
Resources
This model may use your data for training
