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

techxsarthak · January 11, 2025, 4:18pm

`🧩 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.

blocks (23)

blocks (24)

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, 4:21pm

Sample Blocks to message hello to llm

techxsarthak · January 11, 2025, 5:19pm

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 28, 2025, 12:41pm

DeepSeek R1 is now supported

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

techxsarthak · February 18, 2025, 2:02pm

Qwen coder is now supported

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

Kevinkun · February 18, 2025, 3:00pm

I don't think this blocks are correct. please make some corrections.

Move 'set label. text to ...' to the right place.

Taifun · February 18, 2025, 3:06pm

yes, exactly

Taifun

techxsarthak · February 18, 2025, 3:21pm

Yes By mistake... will make the corrections

techxsarthak · February 18, 2025, 5:24pm

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$

techxsarthak · February 19, 2025, 5:05am

Qwen is now supported

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

techxsarthak · March 19, 2025, 4:51pm

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, 5:03pm

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	-	-	-

Spicy_Topics · March 19, 2025, 5:32pm

Perfect..

What a work buddy!!

Just imagine!!

Nice work.

Congrats and all the best to you. Take my heart

TechInterest · March 21, 2025, 4:58pm

very good extension
you should use it for chatbots and if you have a budget then you can buy the full version, because its affordable

example app i made:

Yiu_Dixon · March 23, 2025, 3:12am

after paid, when one model usage is reached, can switch to another model and keep using?

techxsarthak · March 23, 2025, 3:13am

Yes its possible

Yiu_Dixon · March 23, 2025, 3:19am

$6 is one-off payment right?

techxsarthak · March 23, 2025, 3:19am

Yes updated versions will be free

Yiu_Dixon · March 25, 2025, 1:26pm

Can your paid extension read image?