JADE: Simple Multi-Model Chatbot

I often use LLMs and quickly found myself asking GPT4, Gemini and Claude the same question. I wanted to be able to ask the same question to multiple models, compare their answers and pick the best one.

So I built a simple chatbot that use different LLM APIs. You can create bots with a specific model and prompt. You can select as many bots to answer a question. You can then compare the answers and choose the best one. You can continue the conversation with the best answer, meaning using answer from one model to ask another model.

Multi-Models

JADE a simple Multi-Model chatbot. The idea is to use multiple models within the same conversation. Here are the key points:

1. When asking a question, you can query multiple models and compare their responses to choose the best one.
2. The selected response can be used for the next message across all models.

For example, a response from GPT-4 Omni can be used by Claude Haiku.

I am using the app myself for months now and it's been a great experience at minimum price (around 4$/month) accross all APIs. The app itself is totally free to use for now, I may add a paid and free tier with message limits in the future. But I aim at like 1-3$ per month.

More information

• Get access to all models.

  With JADE, you can easily switch between models like GPT 3.5 or 4o, Gemini, Llama, Mistral, Claude, and more. Even custom endpoint.
  
  This means you can choose the best model for your specific needs, whether it's for general knowledge, creative writing, or technical expertise. Having access to multiple models allows you to take advantage of their unique strengths and weaknesses, ensuring you get the most accurate and relevant responses. (See all models available in the last section)
  
  

• Get the best answer from multiple models.

  You can ask a question and receive responses from several models at once, enabling you to compare their answers and choose the most suitable one.
  
  This feature is particularly useful for complex queries where different models might offer unique insights or solutions.
  
  

• Even from the same model.

  The core feature of JADE are the bots. Each bot have a name, model, temperature and system prompt.
  
  You can create as many bot as you want and select as many to answer each question. An example is creating the same model that reponse in different language.
  
  

• Reduce Hallucination.

  AI models sometimes generate information that is inaccurate or misleading, a phenomenon known as "hallucination."
  
  By using multiple models, JADE reduces each model's bias. This ensures that the responses you receive are more reliable and trustworthy.
  
  

• Pay only for what you use or not at all.

  JADE use API, so you get access to free credits or tiers depending of the provider (see next section). This is particularly beneficial for users who may not need to use the chatbot extensively. Once the free credit use, you pay based on the length of you message and the response generated in tokens (a token is around 3 characters). Groq and Google also offer free tiers that are enough for conversation.

• All providers and models.

  OpenAI - OpenAI offer 5$ credits when creating an API account. Around 10 000 small question to GPT-4 Omni or 100 000 to GPT-3.5 Turbo.

  • GPT 4 Omni
  • GPT 4 Turbo
  • GPT 4
  • GPT 3.5 Turbo

  
  

  Anthropic - Anthropic offer 5$ credits when creating an API account. Around 2 000 small question to Claude 3 Opus or 120 000 to Claude Haiku.

  • Claude 3 Opus
  • Claude 3.5 Sonnet
  • Claude 3 Haiku

  
  

  Mistral - Mistral do not offer free credits.

  • Mixtral 8x22b
  • Mixtral 8x7b
  • Mistral 7b
  • Mistral Large
  • Mistral Small
  • Codestral

  
  

  Groq - Groq offer a free tier with limit of tokens and request per minutes. The rate is plenty for a chatbot. 30 messages and between 6 000 and 30 000 tokens per minute. Per tokens coming soon.

  • Llama 3 70b
  • Llama 3 8b
  • Mixtral 8x7b
  • Gemma 7b

  
  

  Google - Like Groq, Google offer a free tier with limit of tokens and request per minutes. The rate is plenty for a chatbot. 15 messages and 1 000 000 tokens per minute. Per tokens also available.

  • Gemini 1.5 pro
  • Gemini 1.5 flash
  • Gemini 1.0 pro

  
  

  Perplexity - Perplexity do not offer a free tier or credits. Perplexity offer what they call 'online' models that can search online. So you can ask for the current weather for example. Those models have additional cost of 5$ per 1 000 requests.

  • Sonar Large
  • Sonar Large Online
  • Sonar Small
  • Sonar Small Online
  • Llama 70b
  • Llama 7b
  • Mixtral 8x7b

  
  

  Fireworks - Fireworks AI offer 1$ of free credits when creating an account. Firework AI have a lot of open source models. I may add fine tuned models in the future.

  • FireLLaVA-13B
  • Mixtral MoE 8x7B Instruct
  • Mixtral MoE 8x22B Instruct
  • Llama 3 70B Instruct
  • Bleat
  • Chinese Llama 2 LoRA 7B
  • DBRX Instruct
  • Gemma 7B Instruct
  • Hermes 2 Pro Mistral 7b
  • Japanese StableLM Instruct Beta 70B
  • Japanese Stable LM Instruct Gamma 7B
  • Llama 2 13B French
  • Llama2 13B Guanaco QLoRA GGML
  • Llama 7B Summarize
  • Llama 2 13B
  • Llama 2 13B Chat
  • Llama 2 70B Chat
  • Llama 2 7B
  • Llama 2 7B Chat
  • Llama 3 70B Instruct (HF version)
  • Llama 3 8B (HF version)
  • Llama 3 8B Instruct
  • Llama 3 8B Instruct (HF version)
  • LLaVA V1.6 Yi 34B
  • Mistral 7B
  • Mistral 7B Instruct
  • Mistral 7B Instruct v0.2
  • Mistral 7B Instruct v0p3
  • Mixtral MoE 8x22B
  • Mixtral MoE 8x22B Instruct (HF version)
  • Mixtral MoE 8x7B
  • Mixtral MoE 8x7B Instruct (HF version)
  • MythoMax L2 13b
  • Nous Hermes 2 - Mixtral 8x7B - DPO (fp8)
  • Phi 3 Mini 128K Instruct
  • Phi 3 Vision 128K Instruct
  • Qwen1.5 72B Chat
  • StableLM 2 Zephyr 1.6B
  • StableLM Zephyr 3B
  • StarCoder 15.5B
  • StarCoder 7B
  • Traditional Chinese Llama2
  • Capybara 34B
  • Yi Large

  
  Hugging face - You can also use custom endpoints. I only tested hugging face but in theory, as long as the key is valid and it use the openai api, it should work. This part need some testing and improvement.
  
  Goose AI - Chat API will be available soon.