[Freemium] GroqText: 30+ LLMs including DeepSeek, Llama, Gemma, ALLaM, Mixtral and Qwen (Search / Code Execution / Vision Models / Streaming and more)

techxsarthak · January 11, 2025, 5:31pm

`🧩 GroqText`

An extension for MIT App Inventor 2.
Extension to integrate AI Text and Vision Models in applications using Groq API with streaming support. My other extensions
Built by Sarthak Gupta

Specifications

Package: com.sarthakdev.groqtext
Size: 20.68 KB
Version: 1.2
Minimum API Level: 7
Updated On: 2025-05-25T18:30:00Z
Built & documented using: FAST-CLI v2.8.1
Extension License: here

Introduction

Integrate a large number of AI Models in your app through the groq api
Includes a generous free plan with daily rate limit (without credit card)
Includes 2b, 8b and 70b parameter models

Features of Groq Inference

Lightning fast AI Models
Supports 30+ AI Models from 5+ providers
Best Free Plan that gives 500k tokens* daily for free to use in production

`Events:`

GroqText has total 5 events.

GroqStreamResponseReceived

Event triggered when a streaming response part is received

Parameter	Type
partialContent	text

CustomStructuredOutputReceived

Event triggered when custom structured output is received from the Groq API

Parameter	Type
jsonOutput	text

GroqResponseReceived

Event triggered when AI response is received

Parameter	Type
statusCode	number
response	text
messageContent	text
finishReason	text
model	text
queueTime	text
promptTokens	text
completionTokens	text

GroqRequestError

Event triggered when an error occurs in Groq API request

Parameter	Type
errorMessage	text

GroqMessageContentReceived

Event triggered when AI message content is extracted

Parameter	Type
messageContent	text

`Methods:`

GroqText has total 5 methods.

ExtractJSONValue

Extract a specific value from the JSON response

Parameter	Type
jsonString	text
fieldPath	text

AskQuestion

Ask a question to the AI

Parameter	Type
userMessage	text

ProcessImage

Process an image with a text prompt using a local image path

Parameter	Type
prompt	text
imagePath	text

RequestCustomStructuredOutput

Request custom structured output from Groq API

Parameter	Type
apiKey	text
modelName	text
systemInstruction	text
userRequest	text
customSchema	text

ResetConversation

Reset the conversation by clearing the chat history

`Setters:`

GroqText has total 11 setter properties.

ApiKey

Set the Groq API Key

Input type: text

ModelName

Set the AI Model Name for text tasks

Input type: text
Helper class: ModelName
Helper enums: Llama_3_3_70b_Versatile, Llama_3_1_8b_Instant, Llama3_70b_8192, Llama3_8b_8192, Gemma2_9b_It, Meta_Llama_Llama_Guard_4_12B, Allam_2_7b, DeepSeek_R1_Distill_Llama_70b, Meta_Llama_4_Maverick, Meta_Llama_4_Scout, Mistral_Saba_24b, Qwen_Qwq_32b, Compound_Beta, Compound_Beta_Mini

VisionModelName

Set the AI Model Name for vision tasks

Input type: text
Helper class: VisionModelName
Helper enums: Llama_4_Scout, Llama_4_Maverick

ApiUrl

Set the API Endpoint URL

Input type: text

SystemMessage

Set the system message for the AI

Input type: text

ChatHistoryEnabled

Enable or disable chat history

Input type: boolean

Temperature

Set the temperature

Input type: number

MaxTokens

Set the max tokens

Input type: number

TopP

Set the top P value

Input type: number

StreamResponses

Set whether to stream responses for text and vision tasks

Input type: boolean

Stop

Set the stop value

Input type: text

`Getters:`

GroqText has total 11 getter properties.

ApiKey

Set the Groq API Key

Return type: text

ModelName

Set the AI Model Name for text tasks

Return type: text

VisionModelName

Set the AI Model Name for vision tasks

Return type: text

ApiUrl

Set the API Endpoint URL

Return type: text

SystemMessage

Set the system message for the AI

Return type: text

ChatHistoryEnabled

Enable or disable chat history

Return type: boolean

Temperature

Set the temperature

Return type: number

MaxTokens

Set the max tokens

Return type: number

TopP

Set the top P value

Return type: number

StreamResponses

Set whether to stream responses for text and vision tasks

Return type: boolean

Stop

Set the stop value

Return type: text

Try the extension for free with GroqTextMini (Free)

This is the difference b/w free and paid version.

GroqTextMini	GroqText
Free	Paid(5.99$)
Use llama-8b model	Use 30+ AI Models (Lllama, Gemma, Mixtral, DeepSeek, Qwen, Distilled models)
8b model	1b, 2b, 3b, 8b, 32b, 70b, 80b models
500 tokens	Unlimited tokens depending on model capacity
No Image Support	Image Support
No Code Execution	Code Execution Support
No Search Support	Search Support

GroqTextMini: com.sarthakdev.groqtextmini.aix (8.3 KB)

Purchase full GroqText extension from here for only 5.99$

Purchase Extension

You can purchase the extension instantly from the link below for just 5.99$

techxsarthak · January 11, 2025, 5:33pm

Extract JSON value Function

ExtractJSONValueBlock

Sample Json
{"id":"chatcmpl-7ceff50a-a5f1","object":"chat.completion","created":
1736604854,"model": "llama3-8b-8192","choices":
[{"index":0,"message":{"role":"assistant","content":"Hello! It's nice to meet you. Is there something I can help you with or would you like to chat?"},"logprobs":null,"finish_reason":"stop"}],"usage": {"queue_time":0.017792521000000002,"prompt_tokens":
11,"prompt_time":0.001729597,"completion_tokens": 25,"completion_time":0.020833333,"total_tokens":
36,"total_time":0.02256293},"system_fin
gerprint":"fp_a9","x_groq": {"id":"req_01jhavea"}}

choices[0].message.content : Get content of message sent by assistant
choices[0].finish_reason: Get the reason for the stop of the generation
model : Get the model name
usage.queue_time : Get the queue time
usage.prompt_tokens : Get the prompt tokens
usage.completion_rokens : Get the completion tokens

techxsarthak · January 11, 2025, 6:24pm

Please contact me via dm for any questions or reply here. I will try to answer as soon as possible.

techxsarthak · January 29, 2025, 9:43am

New Models Support

The extension now supports DeepSeek R1
Here’s the ID: deepseek-r1-distill-llama-70b

techxsarthak · February 15, 2025, 6:46am

Introducing GroqTextMini (Free)

Features

Use llama-8b-8192 model in your app
Limit of maximum 500 tokens per response
Check the difference between paid and free aix

GroqTextMini	GroqText
Free	Paid(5.99$)
Use llama-8b model	Use 15+ AI Models (Lllama, Gemma, Mixtral, DeepSeek, Qwen, Distilled models)
8b model	1b, 2b, 3b, 8b, 32b, 70b, 80b models
500 tokens	Unlimited tokens depending on model capacity

Download aix

com.sarthakdev.groqtextmini.aix (8.3 KB)

If you want to get GroqText extension you can get it from here for only 5.99$

Edouard_Neih · March 14, 2025, 11:47pm

Hi !

I purchased your extension after testing the mini version.

It’s truly extraordinary.

Thank you for this incredible extension.

techxsarthak · March 19, 2025, 5:07pm

Qwen coder is now supported

The extension now supports Alibaba Qwen
Here’s the ID: qwen-2.5-coder-32b

Qwen is now supported

The extension now supports Alibaba Qwen QWQ
Here’s the ID: qwen-qwq-32b

Mistral Saba is now supported

The extension now supports Mistral Saba
Here’s the ID: mistral-saba-24b

Distilled models are now supported

The extension now supports distilled llama, qwen and deepseek models
Here’s the ID: deepseek-r1-distill-qwen-32b, deepseek-r1-distill-llama-70b-specdec, deepseek-r1-distill-llama-70b

techxsarthak · March 19, 2025, 5:08pm

Updated Free Daily tokens and Rate Limits

Groq now supports 17 leading AI models from different providers all under a single API Key with daily free token usage

Model ID	RPM	RPD	TPM	TPD	ASH	ASD
deepseek-r1-distill-llama-70b	30	1,000	6,000	-	-	-
deepseek-r1-distill-qwen-32b	30	1,000	6,000	-	-	-
gemma2-9b-it	30	14,400	15,000	500,000	-	-
llama-3.1-8b-instant	30	14,400	20,000	500,000	-	-
llama-3.1-70b-versatile	30	14,400	6,000	200,000	-	-
llama-3.2-1b-preview	30	7,000	7,000	500,000	-	-
llama-3.2-3b-preview	30	7,000	7,000	500,000	-	-
llama-3.3-70b-specdec	30	1,000	6,000	100,000	-	-
llama-3.3-70b-versatile	30	1,000	6,000	100,000	-	-
llama-guard-3-8b	30	14,400	15,000	500,000	-	-
llama3-8b-8192	30	14,400	30,000	500,000	-	-
llama3-70b-8192	30	14,400	6,000	500,000	-	-
mistral-saba-24b	30	1,000	6,000	-	-	-
mixtral-8x7b-32768	30	14,400	5,000	500,000	-	-
qwen-2.5-32b	30	1,000	6,000	-	-	-
qwen-2.5-coder-32b	30	1,000	6,000	-	-	-
qwen-qwq-32b	30	1,000	6,000	-	-	-

techxsarthak · March 20, 2025, 6:48pm

The extension is at a price of 6$ for this week only after that the prices will increase. So be quick

techxsarthak · April 4, 2025, 11:23am

Version 1.1

This is a major update with new blocks and awesome feature additions. Such as Chat history, System tone and Json structured output.

New Blocks

Chat History: The LLM now has access to all of your previously sent messages.

Disabled by default, Enable by setting the block to true

Reset Conversation history

Set Tone (System Instruction of the AI Model)

Eg. You are a developer.

Structured JSON output

RequestCustomStructuredOutput

UserRequest= Question to ask to the AI
customScheme= The json type to generate

For eg.

Output

Existing users, please dm me to get the latest version.

techxsarthak · April 4, 2025, 11:24am

Create Your Own AI “Mini-APIs” in App Inventor — The Simple Way with GroqText!

No more battling messy AI text! Say hello to clean, structured data with your own AI-powered features inside App Inventor.

Ever ask an AI something, only to get back a long blob of text that’s impossible to use without hours of parsing?
Wish you could just get exactly the info you need, in a format your app understands — right away?

it’s way simpler than you might think.

By combining the GroqText Extension with a smart prompt strategy — asking the AI to reply in JSON format — you can build reliable, custom AI tools that work seamlessly in your App Inventor apps.

Think of it like creating a lightweight, personal API — powered by Groq — without any server setup or advanced coding skills!

What Makes This So Powerful?

On-Demand AI Features
Instant translations, summaries, keyword detection, emotion analysis — you name it. You can create mini-AI tools for almost any use case.

Consistent, Structured Output
By using JSON responses, you get clean data like { "summary": "...", "keywords": [...] }, ready to use in your blocks with no guesswork.

Tidy, Simple Logic
Forget the spaghetti of text parsing. Your block logic becomes clean and easy to follow.

Why It’s a Perfect Fit for App Inventor

You Write the “Function” as a Prompt
Just describe what you want and how the response should look.

Built-in Tools for Decoding

use the inbuilt json parsing block for parsing text using field path.

Easy Data Handling
Use a simple “lookup in pairs” block to get the exact value you need from the dictionary — like the summary, translation, or anything else.

A Sample Workflow:

Send a prompt with GroqText asking for JSON
Get the response in the GotText event
Decode it with ExtractValuefromJSON
Done!

No external servers. No complicated parsing. No fuss.
Just visual blocks and the power of GroqText doing exactly what you ask — in a format that fits right into your app.

Ready to level up your projects? Install the GroqText extension, craft a clear JSON-based prompt, and start building smart, AI-enhanced features in minutes — right from App Inventor.

techxsarthak · April 4, 2025, 11:24am

Developers literally after seeing the features of GroqText extension at such a low price

techxsarthak · April 7, 2025, 4:08pm

New Update

GroqVision is now free with GroqText

techxsarthak · April 9, 2025, 4:35pm

Llama 4 is now supported!

The model that has overthrown Gemma, Mistral and Gemini 2.0

Llama 4 Scout, a 17 billion active parameter model with 16 experts, is the best multimodal model in the world in its class and is more powerful than all previous generation Llama models, while fitting in a single NVIDIA H100 GPU. Additionally, Llama 4 Scout offers an industry-leading context window of 10M and delivers better results than Gemma 3, Gemini 2.0 Flash-Lite, and Mistral 3.1 across a broad range of widely reported benchmarks.

Here’s the ID: meta-llama/llama-4-scout-17b-16e-instruct

techxsarthak · April 9, 2025, 4:35pm

Llama 4 Maverick is here!

The model that has overthrown GPT 4o, Gemini 2.0 flash and DeepSeek v3

Llama 4 Maverick, a 17 billion active parameter model with 128 experts, is the best multimodal model in its class, beating GPT-4o and Gemini 2.0 Flash across a broad range of widely reported benchmarks, while achieving comparable results to the new DeepSeek v3 on reasoning and coding—at less than half the active parameters. Llama 4 Maverick offers a best-in-class performance to cost ratio with an experimental chat version scoring ELO of 1417 on LMArena.

Here’s the ID: meta-llama/llama-4-maverick-17b-128e-instruct

techxsarthak · May 1, 2025, 7:58am

Introducing Compound-Beta: Enhanced AI Capabilities with External Tools

While Large Language Models (LLMs) excel at generating text, Compound-Beta takes the next step. It’s an advanced AI system designed to solve problems by taking action and intelligently using external tools, alongside powerful Llama models.

Key Features

Access to Real-Time Information: Compound-Beta interacts with external environments, providing more accurate and up-to-date responses than an LLM alone.
Multi-Tool Support: Two agentic tool systems available: compound-beta and compound-beta-mini.

Agentic Tool Systems

Compound-Beta

Supports multiple tool calls per request.
Ideal for use cases requiring:
- Multiple web searches per request.
- Multiple code executions per request.

Compound-Beta-Mini

Supports a single tool call per request.
Ideal for use cases requiring:
- A single web search per request.
- A single code execution per request.
Performance: Average of 3x lower latency compared to Compound-Beta.

Available Tools

Both Compound-Beta systems support the following tools:

Web Search: Via Tavily.
Code Execution: Via E2B (Python support only).

Note: Custom user-provided tools are not supported at this time.

techxsarthak · May 1, 2025, 7:58am

Power of Compound LLM

User: make a query to the spacex api and print its response
AI: To make a query to the SpaceX API and print its response, I will use the requests library in Python to send a GET request to the API endpoint. Based on the search results, I found that the SpaceX API has several endpoints for different types of data. The most relevant endpoint for this task appears to be https://api.spacexdata.com/v4/launches/latest. This endpoint returns information about the latest launch.

Here is the Python code to make a query to the SpaceX API and print its response:

import requests
import json

def get_latest_launch():
    url = 'https://api.spacexdata.com/v4/launches/latest'
    try:
        response = requests.get(url)
        response.raise_for_status()  # Raise an exception for HTTP errors
        return response.json()
    except requests.RequestException as e:
        print(f"An error occurred: {e}")
        return None

latest_launch = get_latest_launch()
print(json.dumps(latest_launch, indent=4))

This code sends a GET request to the https://api.spacexdata.com/v4/launches/latest endpoint and prints the response in a JSON format.

The response from the API includes various details such as the launch date, rocket used, crew members, and more. Here is an example of the response:

{
    "fairings": null,
    "links": {
        "patch": {
            "small": "https://images2.imgbox.com/eb/d8/D1Yywp0w_o.png",
            "large": "https://images2.imgbox.com/33/2e/k6VE4iYl_o.png"
        },
        "reddit": {
            "campaign": null,
            "launch": "https://www.reddit.com/r/spacex/comments/xvm76j/rspacex_crew5_launchcoast_docking_discussion_and/",
            "media": null,
            "recovery": null
        },
        "flickr": {
            "small": [],
            "original": []
        },
        "presskit": null,
        "webcast": "https://youtu.be/5EwW8ZkArL4",
        "youtube_id": "5EwW8ZkArL4",
        "article": null,
        "wikipedia": "https://en.wikipedia.org/wiki/SpaceX_Crew-5"
    },
    "static_fire_date_utc": null,
    "static_fire_date_unix": null,
    "net": false,
    "window": null,
    "rocket": "5e9d0d95eda69973a809d1ec",
    "success": true,
    "failures": [],
    "details": null,
    "crew": [
        "62dd7196202306255024d13c",
        "62dd71c9202306255024d13d",
        "62dd7210202306255024d13e",
        "62dd7253202306255024d13f"
    ],
    "ships": [],
    "capsules": [
        "617c05591bad2c661a6e2909"
    ],
    "payloads": [
        "62dd73ed202306255024d145"
    ],
    "launchpad": "5e9e4502f509094188566f88",
    "flight_number": 187,
    "name": "Crew-5",
    "date_utc": "2022-10-05T16:00:00.000Z",
    "date_unix": 1664985600,
    "date_local": "2022-10-05T12:00:00-04:00",
    "date_precision": "hour",
    "upcoming": false,
    "cores": [
        {
            "core": "633d9da635a71d1d9c66797b",
            "flight": 1,
            "gridfins": true,
            "legs": true,
            "reused": false,
            "landing_attempt": true,
            "landing_success": true,
            "landing_type": "ASDS",
            "landpad": "5e9e3033383ecbb9e534e7cc"
        }
    ],
    "auto_update": true,
    "tbd": false,
    "launch_library_id": "f33d5ece-e825-4cd8-809f-1d4c72a2e0d3",
    "id": "62dd70d5202306255024d139"
}

This response provides information about the latest launch, including the launch date, rocket used, crew members, and more.

This is the power of Groq Compound LLMs search, execute code!

Ahmed10 · May 2, 2025, 10:32pm

Does Groq extension has the ability to create continuous chat context or handle streamed chunks of text response ? these are very important features .

techxsarthak · May 4, 2025, 5:06am

Try the free version you’ll love it

techxsarthak · May 4, 2025, 5:07am

The extension has the ability to enable chat history that means llm remembers what was said to it earlier