Retired May 2026
Grok 4 Fast (Non-Reasoning)
Non-reasoning mode of Grok 4 Fast, released September 2025, sharing unified weights with the reasoning variant and prompt-steered for low-latency responses.
Key Specifications
- Context window
- 2M tokens
- Released
- Inputs
- Text, image
- Capabilities Show details
- 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 Fast (Non-Reasoning) good for?
Low-latency responses without a reasoning step, which suited classification, extraction and summarising across large documents. It took text and images.
When is Grok 4 Fast (Non-Reasoning) not a good fit?
Any new work: xAI retired it in May 2026, and its migration guide points to Grok 4.3 with reasoning effort set to none. No built-in web search or code execution, and closed weights.
How does Grok 4 Fast (Non-Reasoning) compare with Grok 4.1 Fast (Non-Reasoning)?
xAI says Grok 4.1 Fast (Non-Reasoning) got long-horizon reinforcement learning in simulated tool environments across dozens of domains, with a focus on multi-turn agent work, and hallucinates much less than Grok 4 Fast (Non-Reasoning). It launched with xAI's Agent Tools API. Same 2M-token context and text and image input. Grok 4 Fast (Non-Reasoning) came out 2 months earlier.
Can I self-host Grok 4 Fast (Non-Reasoning)?
No. xAI does not publish the weights; Grok 4 Fast (Non-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 4.1 Fast (Reasoning)
|
2M | ||
|
Grok 4
|
256K | ||
|
Grok 3
|
131K | ||
|
Grok 3 Mini
|
131K | ||
|
Grok 4 Fast (Reasoning)
|
2M | ||