Retired May 2026
Grok 4.1 Fast (Reasoning)
Reasoning variant of Grok 4.1 Fast, released November 2025, built on unified weights shared with the non-reasoning variant and steered toward multi-step reasoning with fewer hallucinations.
Key Specifications
- Context window
- 2M tokens
- Knowledge cutoff
- Released
- Inputs
- Text, image
- Capabilities Show details
- Reasoning Thinks before it answers, always on or as a switchable mode. Function calling Connect to external tools, APIs, and systems. Structured output Return responses in structured formats like JSON.
Frequently Asked Questions
What is Grok 4.1 Fast (Reasoning) good for?
Multi-step reasoning that suited agent loops and analysing long documents in one call. It took text and images, and xAI says it hallucinated less than the models before it.
When is Grok 4.1 Fast (Reasoning) not a good fit?
Any new work: xAI retired it in May 2026, and its migration guide points to Grok 4.3 with low reasoning effort. No built-in web search or code execution, and closed weights.
How does Grok 4.1 Fast (Reasoning) compare with Grok 4 Fast (Reasoning)?
xAI says Grok 4.1 Fast (Reasoning) was trained with long-horizon reinforcement learning in simulated tool environments across dozens of domains, holds up better over long multi-turn agent runs, and hallucinates much less than Grok 4 Fast (Reasoning). It launched alongside xAI's Agent Tools API. Same 2M-token context and text and image input. Grok 4.1 Fast (Reasoning) came out 2 months later.
Can I self-host Grok 4.1 Fast (Reasoning)?
No. xAI does not publish the weights; Grok 4.1 Fast (Reasoning) is available only through hosted APIs.
More from xAI
| Model | Context | Input /1M | Output /1M |
|---|---|---|---|
|
Grok 4.5
|
500K | $2.00 | $6.00 |
|
Grok 4.6
|
500K | $2.00 | $6.00 |
|
Grok 4.1 Fast (Non-Reasoning)
|
2M | ||
|
Grok 4
|
256K | ||
|
Grok 3
|
131K | ||
|
Grok 3 Mini
|
131K | ||
|
Grok 4 Fast (Non-Reasoning)
|
2M | ||
|
Grok 4 Fast (Reasoning)
|
2M | ||