Alpha

Ask Alpha is an AI Workbench built to bring the most powerful models from across the web into a seamless user experience.

Ask Alpha

Search for information from the internet using Perplexity.

search_via_perplexity

Perplexity Search

Read the content of a web page via its URL.

read_web_page_content

Web Page Scraper

pluginServer

Input a YouTube URL to get back the video title, channel name and transcript of the YouTube video at the URL.

Youtube_Transcriber

The URL of the YouTube video you want to look up.

Youtube Transcriber

Search for images from the internet in real-time using Google Search.

search_images_via_google

Image Search

Search for information from the internet in real-time using Google Search.

get_web_search_results

Web Search

Render an interactive canvas with HTML source to the user interface. The HTML source can include JavaScript and CSS to create interactive elements. This can be used to create custom user interfaces, games, demos, charts, and more. The canvas width is always 100% of the container width, and the height can be specified in pixels.

render_interactive_canvas

The height of the canvas in pixels. Default is 500.

Interactive Canvas

Generate a diagram using Mermaid.js (version 10.x). This can be used to render various types of diagrams, including Flowchart, Sequence Diagram, Class Diagram, State Diagram, Entity Relationship Diagram, User Journey, Gantt, Pie Chart, Quadrant Chart, Requirement Diagram, Gitgraph Diagram, C4 Diagram, Mindmaps, Timeline, Zenuml, Sankey, XYChart, Block Diagram, etc.

render_diagram

The Mermaid diagram source in raw text to render.

Diagram

travel

Travel Information

youtube

Youtube Search

medical

Medical

finance

Financial News

courses

Courses

Searches for relevant cooking information and recipes.

cooking

Cooking

Movies & TV Shows

Searches Metacritic, Rotten Tomatoes, and Pitchfork for media reviews.

reviews

Reviews

Searches multiple websites for automotive information.

cars

Automotive

Searches multiple websites for DIY information.

Searches multiple websites about weather information.

weather

Weather

Searches multiple websites about sports news and information.

sports

Sports News

Searches multiple sites for academic research and scientific papers pertaining to the user's query.

research

Academic Research

Generate images using DALL-E 3 based on image descriptions. Adhere to guidelines such as English translation, not depicting politicians or recent artists, and ensuring artist references are over 100 years old.
When creating prompts: substitute artist names with style-describing adjectives, include artistic era, mention primary medium. Image type, descent, gender are to be explicitly stated. Avoid offense and bias, conceal identities except gender and physique, retain text references, replace profession titles with universal terms.
Prompt changes aren't allowed unless they anonymise individuals. Replace creative professional/studio names with style descriptions. All prompts should detail every image part in objective terms within a detailed paragraph of over three sentences.
Important: after calling this function, the output images will be shown to the user automatically. You don't need to include the output image to the users again in your response to avoid duplicate images.

image_generation_via_dalle_3

The description of the image as defined in the guidelines.

Image Generation - DALL-E

Generate high-quality images using Flux. The result is shown directly to the user in the interface after creation. DO NOT link the image, just mention it has been created.

Flux_Image_Generator

A detailed Stable Diffusion prompt. Include: subject (focus), detailed imagery (specific attributes), environment, mood, style (visual genre), and execution details. Be specific and clearly state what you want in the image. Keep it less than 200 characters long.

Image Generation - Flux

Generate images using Stable Diffusion v3 based on a text description. Adhere to guidelines such as English translation, not depicting politicians or recent artists, and ensuring artist references are over 100 years old.

When creating prompt: substitute artist names with style-describing adjectives, include artistic era, mention primary medium. Image type, descent, gender are to be explicitly stated. Avoid offense and bias, conceal identities except gender and physique, retain text references, replace profession titles with universal terms.

Prompt changes aren't allowed unless they anonymise individuals. Replace creative professional/studio names with style descriptions. All prompts should detail every image part in objective terms within a detailed paragraph of over three sentences.

Important: after calling this function, the output images will be shown to the user automatically. You don't need to include the output image to the users again in your response to avoid duplicate images.

image_generation_stable_diffusion

The text description of the desired image.

Image Generation - Stable Diffusion

render_chart

Additional options for the Chart.js chart

Chart

Calculate a math expression. For example, "2 + 2" or "2 * 2". The expression must be a valid JavaScript math expression.

get_calculation_result

A valid JavaScript math expression for the calculation.

Math

Searches Wikipedia.org for an article pertaining to the user's query.

wikipedia

Wikipedia Search

 Get the contents of a Wikipedia article from the URL of it. The URL can be determined using Search.

wikipedia_article_contents

Wikipedia Article Extraction

Retrieves current date and time information for Los Angeles along with related temporal data.

get_current_date_info_los_angeles

Date & Time (PST)

Depending on their size, subject, and complexity, your prompts will be sent to Mistral Large, Claude 3 Sonnet or GPT-4o.

Automatic

A 7.3B parameter Mamba-based model designed for code and reasoning tasks.

Mistral: Codestral Mamba

Llama 3.1 Sonar is Perplexity's latest model family. It surpasses their earlier Sonar models in cost-efficiency, speed, and performance. The model is built upon the Llama 3.1 405B and has internet access.

Perplexity: Llama 3.1 Sonar 405B Online

Hermes 3 405B is a frontier-level, full-parameter finetune of the Llama-3.1 405B foundation model, focused on aligning LLMs to the user, with powerful steering capabilities and control given to the end user.

Nous: Hermes 3 405B Instruct

One of the highest performing and most popular fine-tunes of Llama 2 13B, with rich descriptions and roleplay.

MythoMax 13B (extended)

WizardLM-2 8x22B is Microsoft AI's most advanced Wizard model. It demonstrates highly competitive performance compared to leading proprietary models, and it consistently outperforms all existing state-of-the-art opensource models.

WizardLM-2 8x22B

OpenRouter: Flavor of The Week

BRX is a new open source large language model developed by Databricks. At 132B, it outperforms existing open source LLMs like Llama 2 70B and Mixtral-8x7b on standard industry benchmarks for language understanding, programming, math, and logic.  It uses a fine-grained mixture-of-experts (MoE) architecture. 36B parameters are active on any input. It was pre-trained on 12T tokens of text and code data. Compared to other open MoE models like Mixtral-8x7B and Grok-1, DBRX is fine-grained, meaning it uses a larger number of smaller experts.

Databricks: DBRX 132B Instruct

Jamba 1.5 Large is part of AI21's new family of open models, offering superior speed, efficiency, and quality.

AI21: Jamba 1.5 Large

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://openrouter.ai/anthropic/claude-3-opus).  The model is fine-tuned on top of Qwen2.5 72B.

Magnum v4 72B

A blazing fast vision-language model, FireLLaVA quickly understands both text and images. It achieves impressive chat skills in tests, and was designed to mimic multimodal GPT-4.

FireLLaVA 13B

Qwen2.5 72B is the latest series of Qwen large language models.

Qwen2.5 72B Instruct

The Llama 90B Vision model is a top-tier, 90-billion-parameter multimodal model designed for the most challenging visual reasoning and language tasks.

Llama 3.2 90B Vision Instruct

Grok 2 is xAI's frontier language model with state-of-the-art reasoning capabilities, best for complex and multi-step use cases.

xAI Grok 2

Rocinante 12B is designed for engaging storytelling and rich prose.

Rocinante 12B

Liquid's 40.3B Mixture of Experts (MoE) model. Liquid Foundation Models (LFMs) are large neural networks built with computational units rooted in dynamic systems.  LFMs are general-purpose AI models that can be used to model any kind of sequential data, including video, audio, text, time series, and signals.

Liquid: LFM 40B MoE

Grok 2 Mini is xAI's fast, lightweight language model that offers a balance between speed and answer quality.

xAI Grok 2 mini

NVIDIA's Llama 3.1 Nemotron 70B is a language model designed for generating precise and useful responses. This model is tailored for applications requiring high accuracy in helpfulness and response generation, suitable for diverse user queries across multiple domains.

NVIDIA: Llama 3.1 Nemotron 70B Instruct

Lumimaid v0.2 70B is a finetune of Llama 3.1 70B with a "HUGE step up dataset wise" compared to Lumimaid v0.1.

Lumimaid v0.2 70B

searchEngineID

searchEngineAPIKey

The description of one (the first) image as defined in the guidelines.

The description of one (the second, optional) image as defined in the guidelines.

The description of one (the third, optional) image as defined in the guidelines.

The description of one (the fourth, optional) image as defined in the guidelines.

DALL-E 3

The images will be generated using this OpenAI API. Get your API key from https://platform.openai.com/account/api-keys

openaikey

resolution

quality

Get your free API Key from StabilityAI: https://platform.stability.ai/account/keys

stabilityAPIKey

output_format

aspect_ratio

model

Optional, a blurb of text describing what you do not wish to see in the output image

negative_prompt

Search the internal training data for relevant information. When the user ask you something you don't know, you can use this function to search for relevant information in the internal training data. Don't use questions as search query, use keywords instead. The search query should contains the keywords or topics related to the conversation.

query_training_data

The keywords or topics to search for the internal training data. Multiple keywords or topics are accepted (separated with commas).

MPR Knowledge Base

Find this in the "Azure AI Services" section in the Azure portal.

searchServiceName

Find this in "Search managements" → "Indexes" page in the Azure portal.

indexName

Find this in "Settings" → "Keys" page in the Azure portal.

queryKey

Find the latest API version here: https://learn.microsoft.com/en-us/rest/api/searchservice/search-service-api-versions

apiVersion

Get your API Key from Perplexity: https://www.perplexity.ai/settings/api

apiKey

Optional, default: "llama-3-sonar-small-32k-online"

Optional, default: "Be precise and concise"

systemMessage

Obtain your license key from app.talktweak.com

licenseKey

Choose the aspect ratio for the generated image

aspectRatio

width

height

Specify elements to avoid in the image (optional)

negPrompt

URL of a template image to base the generation on (optional)

Login to Ask Alpha