Grok 4.1 Fast (Reasoning)
Intelligence
38.6
#99/523
Coding
30.9
#124/429
Math
89.3
#31/265
Speed
113 tok/s
TTFT: 6.96s
Pricing
$0.20 / $0.50
per 1M tokens (in/out)
Bringing the next generation of tool-calling agents to the xAI API. Grok-4.1 Fast Reasoning is a high-speed variant optimized for faster inference while maintaining strong reasoning capabilities through thinking tokens.
Grok 4.1 Fast (Reasoning) by xAI is designed for high-speed reasoning tasks. It processes at 113.399 tokens per second and is priced at $0.2 per million input tokens, targeting professional users.
When to Use Grok 4.1 Fast (Reasoning)
✓ Best For
- Complex reasoning tasks
- Data analysis requiring high mathematical accuracy
- Programming assistance with a focus on logic
✗ Not Ideal For
- Basic conversational tasks
- Applications requiring extensive coding capabilities
How Grok 4.1 Fast (Reasoning) Compares
Intelligence Index · Higher is better
AlibabaOpenAIxAIStepFunInclusionAI
Benchmark Profile
Coding Index
ByteDance SeedNVIDIAxAIOpenAIAnthropic
Math Index
AmazonDeepSeekxAIOpenAIInclusionAI
Intelligence · Coding · Math
Intelligence
Coding
Math
All Benchmark Scores (15)
| Benchmark | Score | |
|---|---|---|
| Intelligence Index | 38.6 | |
| Coding Index | 30.9 | |
| Math Index | 89.3 | |
| MMLU-Pro | 854% | |
| GPQA | 853% | |
| LiveCodeBench | 822% | |
| HLE | 176% | |
| SciCode | 44.2% | |
| IFBench | 52.7% | |
| LCR | 68% | |
| TerminalBench Hard | 24.2% | |
| Tau2 | 93.3% | |
| AIME 2025 | 89.3% | |
| Arena Chat | 10.9 | |
| Arena Coding | 6.4 |
Data: Artificial Analysis · Updated: April 2, 2026
Frequently Asked Questions (15)
When was Grok 4.1 Fast (Reasoning) released?
Grok 4.1 Fast (Reasoning) was released on November 19, 2025.
Who created Grok 4.1 Fast (Reasoning)?
Grok 4.1 Fast (Reasoning) was created by xAI.
How intelligent is Grok 4.1 Fast (Reasoning)?
Grok 4.1 Fast (Reasoning) scores 39 on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 20).
How fast is Grok 4.1 Fast (Reasoning)?
Grok 4.1 Fast (Reasoning) generates output at 139.3 tokens per second (based on xAI's API), which is above average compared to other reasoning models in a similar price tier (median: 93.8 t/s).
What is the latency of Grok 4.1 Fast (Reasoning)?
Grok 4.1 Fast (Reasoning) has a time to first token (TTFT) of 9.87s (based on xAI's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 1.84s).
How much does Grok 4.1 Fast (Reasoning) cost?
Grok 4.1 Fast (Reasoning) costs $0.20 per 1M input tokens (better than average, median: $0.25) and $0.50 per 1M output tokens (very competitive, median: $0.90), based on xAI's API.
What is Grok 4.1 Fast (Reasoning) API pricing?
Grok 4.1 Fast (Reasoning) costs $0.20 per 1M input tokens and $0.50 per 1M output tokens (based on xAI's API). For a blended rate (3:1 input to output ratio), this is $0.28 per 1M tokens. Pricing may vary by provider.
How verbose is Grok 4.1 Fast (Reasoning)?
When evaluated on the Intelligence Index, Grok 4.1 Fast (Reasoning) generated 53M output tokens, which is somewhat higher than average compared to other reasoning models in a similar price tier (median: 20M).
Is Grok 4.1 Fast (Reasoning) a reasoning model?
Yes, Grok 4.1 Fast (Reasoning) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
What input modalities does Grok 4.1 Fast (Reasoning) support?
Grok 4.1 Fast (Reasoning) supports text and image input.
What output modalities does Grok 4.1 Fast (Reasoning) support?
Grok 4.1 Fast (Reasoning) supports text output.
Can Grok 4.1 Fast (Reasoning) process images?
Yes, Grok 4.1 Fast (Reasoning) supports image input and can analyze, describe, and answer questions about images.
Is Grok 4.1 Fast (Reasoning) multimodal?
Yes, Grok 4.1 Fast (Reasoning) is multimodal. It can process text and image input and generate text output.
What is the context window of Grok 4.1 Fast (Reasoning)?
Grok 4.1 Fast (Reasoning) has a context window of 2.0M tokens. This determines how much text and conversation history the model can process in a single request.
Is Grok 4.1 Fast (Reasoning) open source?
No, Grok 4.1 Fast (Reasoning) is proprietary. The model weights are not publicly available.
