API Key Models Playground GitHub Get Support

grok-3-mini-beta

Previousgrok-3-beta NextImage Models

Last updated 10 days ago

Was this helpful?

grok-3-mini-beta

This documentation is valid for the following list of our models:

x-ai/grok-3-mini-beta

Model Overview

A lighter version of the , designed for quicker response times while maintaining robust reasoning capabilities. It is particularly suited for applications where speed is prioritized over exhaustive accuracy checks.

How to Make a Call

Setup You Can’t Skip

: Visit the AI/ML API website and create an account (if you don’t have one yet). : After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.

Copy the code example

At the bottom of this page, you'll find that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.

Modify the code example

Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key from your account. Insert your question or request into the content field—this is what the model will respond to.

^_(Optional)Adjust other optional parameters if needed

Only model and messages are required parameters for this model (and we’ve already filled them in for you in the example), but you can include optional parameters if needed to adjust the model’s behavior. Below, you can find the corresponding , which lists all available parameters along with notes on how to use them.

Run your modified code

Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.

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 .

API Schema

Code Example (Python)

import requests

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        "Content-Type":"application/json", 

        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"x-ai/grok-3-mini-beta",
        "messages":[
            {
                "role":"user",

                # Insert your question for the model here, instead of Hello:
                "content":"Hello"
            }
        ]
    }
)

data = response.json()
print(data)

Response

{'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}}

Previousgrok-3-beta NextImage Models

Last updated 10 days ago

Was this helpful?

This documentation is valid for the following list of our models:

x-ai/grok-3-mini-beta

Model Overview

How to Make a Call

Setup You Can’t Skip

: Visit the AI/ML API website and create an account (if you don’t have one yet). : After logging in, navigate to your account dashboard and generate your API key. Ensure that key is enabled on UI.

Copy the code example

At the bottom of this page, you'll find that shows how to structure the request. Choose the code snippet in your preferred programming language and copy it into your development environment.

Modify the code example

Replace <YOUR_AIMLAPI_KEY> with your actual AI/ML API key from your account. Insert your question or request into the content field—this is what the model will respond to.

^_(Optional)Adjust other optional parameters if needed

Run your modified code

Run your modified code in your development environment. Response time depends on various factors, but for simple prompts it rarely exceeds a few seconds.

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 .

API Schema

Code Example (Python)

import requests

response = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={
        "Content-Type":"application/json", 

        # Insert your AIML API Key instead of <YOUR_AIMLAPI_KEY>:
        "Authorization":"Bearer <YOUR_AIMLAPI_KEY>",
        "Content-Type":"application/json"
    },
    json={
        "model":"x-ai/grok-3-mini-beta",
        "messages":[
            {
                "role":"user",

                # Insert your question for the model here, instead of Hello:
                "content":"Hello"
            }
        ]
    }
)

data = response.json()
print(data)

Response

{'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}}

Generate a conversational response using a language model.

post

Creates a chat completion using a language model, allowing interactive conversation by predicting the next response based on the given chat history. This is useful for AI-driven dialogue systems and virtual assistants.

Authorizations

Body

modelundefined · enumRequiredAvailable options:

top_kintegerOptional

repetition_penaltynumber · max: 2Optional

min_pnumber · max: 1Optional

top_anumber · max: 1Optional

reasoningobjectOptional

Configuration for model reasoning/thinking tokens

frequency_penaltynumber | nullableOptional

logit_biasobject | nullableOptional

logprobsboolean | nullableOptional

top_logprobsnumber | nullableOptional

max_tokensnumber · min: 1OptionalDefault: 512

max_completion_tokensinteger · min: 1Optional

ninteger | nullableOptional

predictionobjectOptional

presence_penaltynumber | nullableOptional

seedinteger · min: 1Optional

messagesone of[]Required

streambooleanOptionalDefault: false

stream_optionsobjectOptional

top_pnumber · min: 0.1 · max: 1Optional

temperaturenumber · max: 2Optional

stopany ofOptional

toolsobject[]Optional

tool_choiceany ofOptional

parallel_tool_callsbooleanOptional

reasoning_effortstring · enumOptionalAvailable options:

response_formatone ofOptional

JSON object response format. An older method of generating JSON responses. Using json_schema is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so

audioobject | nullableOptional

Parameters for audio output. Required when audio output is requested with modalities: ["audio"]

modalitiesstring · enum[] | nullableOptional

Output types that you would like the model to generate

web_search_optionsobjectOptional

This tool searches the web for relevant results to use in a response

Responses

post

POST /v1/chat/completions HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer <YOUR_AIMLAPI_KEY>
Content-Type: application/json
Accept: */*
Content-Length: 996

{
  "model": "x-ai/grok-3-mini-beta",
  "top_k": 1,
  "repetition_penalty": 1,
  "min_p": 1,
  "top_a": 1,
  "reasoning": {
    "effort": "low",
    "max_tokens": 1,
    "exclude": true
  },
  "frequency_penalty": 1,
  "logit_bias": {
    "ANY_ADDITIONAL_PROPERTY": 1
  },
  "logprobs": true,
  "top_logprobs": 1,
  "max_tokens": 1,
  "max_completion_tokens": 1,
  "n": 1,
  "prediction": {
    "type": "content",
    "content": "text"
  },
  "presence_penalty": 1,
  "seed": 1,
  "messages": [
    {
      "role": "system",
      "content": "text",
      "name": "text"
    }
  ],
  "stream": true,
  "stream_options": {
    "include_usage": true
  },
  "top_p": 1,
  "temperature": 1,
  "stop": "text",
  "tools": [
    {
      "type": "function",
      "function": {
        "description": "text",
        "name": "text",
        "parameters": null,
        "strict": true,
        "required": [
          "text"
        ]
      }
    }
  ],
  "tool_choice": "none",
  "parallel_tool_calls": true,
  "reasoning_effort": "low",
  "response_format": {
    "type": "text"
  },
  "audio": {
    "format": "wav",
    "voice": "alloy"
  },
  "modalities": [
    "text"
  ],
  "web_search_options": {
    "search_context_size": "low",
    "user_location": {
      "approximate": {
        "city": "text",
        "country": "text",
        "region": "text",
        "timezone": "text"
      },
      "type": "approximate"
    }
  }
}

201Success

No content

Model Overview

How to Make a Call

Setup You Can’t Skip

Copy the code example

Modify the code example

(Optional) Adjust other optional parameters if needed

Run your modified code

API Schema

Code Example (Python)

Model Overview

How to Make a Call

Setup You Can’t Skip

Copy the code example

Modify the code example

(Optional) Adjust other optional parameters if needed

Run your modified code

API Schema

Code Example (Python)

Generate a conversational response using a language model.

^_(Optional)Adjust other optional parameters if needed

^_(Optional)Adjust other optional parameters if needed