Retired Aug 2026
Grok 3 Mini
xAI's lightweight reasoning model, released February 2025 and trained with large-scale reinforcement learning for chain-of-thought reasoning.
Key Specifications
- Context window
- 131K tokens
- Knowledge cutoff
- Released
- Inputs
- Text
- 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 3 Mini good for?
Reasoning on text-only tasks where a smaller model was acceptable: xAI built it as its lightweight reasoning model.
When is Grok 3 Mini not a good fit?
Any new work: it left xAI's models page in August 2026, so treat it as retired. Text only, with no built-in web search or code execution.
Can I self-host Grok 3 Mini?
No. xAI does not publish the weights; Grok 3 Mini 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 4 Fast (Non-Reasoning)
|
2M | ||
|
Grok 4 Fast (Reasoning)
|
2M | ||