# grok-3-mini-beta
{% columns %}
{% column width="66.66666666666666%" %}
{% hint style="info" %}
This documentation is valid for the following list of our models:
* `x-ai/grok-3-mini-beta`
{% endhint %}
{% endcolumn %}
{% column width="33.33333333333334%" %} Try in Playground
{% endcolumn %}
{% endcolumns %}
## Model Overview
A lighter version of the [Grok 3 Beta model](https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-3-beta), designed for quicker response times while maintaining robust reasoning capabilities. It is particularly suited for applications where speed is prioritized over exhaustive accuracy checks.
{% hint style="success" %}
[Create AI/ML API Key](https://aimlapi.com/app/keys)
{% endhint %}
How to make the first API call
**1️⃣ Required setup (don’t skip this)**\
▪ **Create an account:** Sign up on the AI/ML API website (if you don’t have one yet).\
▪ **Generate an API key:** In your account dashboard, create an API key and make sure it’s **enabled** in the UI.
**2️ Copy the code example**\
At the bottom of this page, pick the snippet for your preferred programming language (Python / Node.js) and copy it into your project.
**3️ Update the snippet for your use case**\
▪ **Insert your API key:** replace `` with your real AI/ML API key.\
▪ **Select a model:** set the `model` field to the model you want to call.\
▪ **Provide input:** fill in the request input field(s) shown in the example (for example, `messages` for chat/LLM models, or other inputs for image/video/audio models).
**4️ (Optional) Tune the request**\
Depending on the model type, you can add optional parameters to control the output (e.g., generation settings, quality, length, etc.). See the API schema below for the full list.
**5️ Run your code**\
Run the updated code in your development environment. Response time depends on the model and request size, but simple requests typically return quickly.
{% hint style="success" %}
If you need a more detailed walkthrough for setting up your development environment and making a request step by step — feel free to use our [Quickstart guide](https://docs.aimlapi.com/api-references/text-models-llm/xai/broken-reference).
{% endhint %}
## API Schema
{% openapi src="" path="/v1/chat/completions" method="post" %}
{% endopenapi %}
## Code Example
{% tabs %}
{% tab title="Python" %}
{% code overflow="wrap" %}
```python
import requests
import json # for getting a structured output with indentation
response = requests.post(
"https://api.aimlapi.com/v1/chat/completions",
headers={
# Insert your AIML API Key instead of :
"Authorization":"Bearer ",
"Content-Type":"application/json"
},
json={
"model":"x-ai/grok-3-mini-beta",
"messages":[
{
"role":"user",
"content":"Hello" # insert your prompt here, instead of Hello
}
]
}
)
data = response.json()
print(json.dumps(data, indent=2, ensure_ascii=False))
```
{% endcode %}
{% endtab %}
{% tab title="JavaScript" %}
{% code overflow="wrap" %}
```javascript
async function main() {
const response = await fetch('https://api.aimlapi.com/v1/chat/completions', {
method: 'POST',
headers: {
// insert your AIML API Key instead of
'Authorization': 'Bearer ',
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'x-ai/grok-3-mini-beta',
messages:[
{
role:'user',
content: 'Hello' // insert your prompt here, instead of Hello
}
],
}),
});
const data = await response.json();
console.log(JSON.stringify(data, null, 2));
}
main();
```
{% endcode %}
{% endtab %}
{% endtabs %}
Response
{% code overflow="wrap" %}
```json5
{'id': 'gen-1744380893-6fzXa86I1KOoFhg8d7Y8', 'system_fingerprint': 'fp_d133ae3397', 'object': 'chat.completion', 'choices': [{'index': 0, 'finish_reason': 'stop', 'logprobs': None, 'message': {'role': 'assistant', 'content': "Hello! I'm Assistant, here to help. How can I assist you today? 😊", 'reasoning_content': 'First, the user said "Hello." This is a simple greeting. As an AI assistant, my response should be friendly, engaging, and appropriate.\n\nMy role is to be helpful and truthful, based on the instructions. I should continue the conversation naturally.\n\nA good response to "Hello" could be:\n- A greeting back, like "Hi there!" or "Hello! How can I help you?"\n- Since this might be the start of a conversation, I should invite further interaction.\n\nKeep it concise and not overwhelming. People often say "Hello" to test or start a chat.\n\nFinally, end my response in a way that encourages more dialogue, unless it\'s a standalone interaction.\n\nPossible response:\n- "Hello! How are you today?"\n- Or, "Hi! What can I assist you with?"\n\nTo make it more personal, I could reference being an AI, but that might not be necessary right away.\n\nThe system prompt says: "You are a helpful and truthful AI assistant named Assistant." So, I should respond as Assistant.\n\nStructure:\n1. Greet back.\n2. Offer help or ask a question to continue.\n\nFinal response: "Hello! I\'m Assistant, here to help. What\'s on your mind?"', 'refusal': None}}], 'created': 1744380893, 'model': 'x-ai/grok-3-mini-beta', 'usage': {'prompt_tokens': 5, 'completion_tokens': 19, 'total_tokens': 24}}
```
{% endcode %}
---
# Agent Instructions: Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter:
```
GET https://docs.aimlapi.com/api-references/text-models-llm/xai/grok-3-mini-beta.md?ask=
```
The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.
Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.