Movatterモバイル変換


[0]ホーム

URL:


Skip to content

Navigation Menu

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

Sign up

A feature-rich portal to chat with GPT-4, Claude, Gemini, Mistral, & OpenAI Assistant APIs via a lightweight Node.js web app; supports customizable multimodality for voice, images, & files.

License

NotificationsYou must be signed in to change notification settings

Zaki-1052/GPTPortal

Repository files navigation

Welcome to myChat-Bot Portal, a full-featuredNode.js-based web application that allows users to interact with achatbot powered byOpenAI'sGPT-4 API, including the latestVision,Hearing, andSpeaking capabilities withimage-generation,file uploads, and superiorModel Performance fromadvanced andeditableCustom Instructions in theSystem Prompt.

GPTPortal now supports theAnthropic Claude andMistral AI models, plusGoogle Gemini viafree API. Italso includes anativeCode Environment viaAssistants Mode to reusefiles andinstructions from OpenAI'sBeta API!Exploreall the additional features added, likecustomizableChat History,Prompt Templates,easySetup, andmany moreAPI Providers.

IMPORTANT: To view the old documentation (which is still applicable to v2), please see theOld Documentation Here.

Table of Contents

Features

  • Interactivechat interface with support fortext messages.
  • Voice Conversations viaWhisper transcriptions andspoken responses.
  • Image Upload functionality forvisual context in discussions.
  • Server-side integration withSEVENAIAPIproviders andcounting.
  • Basic authentication forsecure access.
  • CustomizableSystem-Defined Instructions andModel Parameters.
  • Simple and intuitiveUI withcopy-to-clipboard features.
  • Markdownrendering for chat messages inMarked styles.
  • Export asHTMLbutton forconversation history.
  • Integratedshutdownfunctionality at "Bye!"
  • Image Generation withDALL·E 3 at "Generate:".
  • File Uploads via manualconcatenation forlarge texts.
  • Assistants API Mode forreusable files andcustom instructions.
    • IncludesAutomatic Python Execution in statefulJupyter Environment.
    • Retrieval Augmented Generation ofuploaded files.
  • NewAnthropic Claude,Google Gemini, &Mistral Models.
  • Keyboard Shortcuts to control variousChatGPT-like functions.
  • Editable Custom Instructions via afrontend UI.
  • Prompt Templates for theSystem viaSidebar.
  • Conversation History withoptimizedcontext windows.
  • AutomaticToken-CostCalculations andSummaries.
  • Model Selector of variousLLM APIs. Includes:
    • GPT-4:EVERY GPT Model Release
      • Includes 4o, Turbo, old v4, 3.5, etc.
    • Gemini:ALL Google Gemini Models
      • IncludesGemini-Pro andFlash
    • Claude Opus-Instant:
      • Seven NewAnthropic HighPerformance Models
    • Mistral:Tiny-Medium
      • SixNewMistral AI Models
    • LLaMA-3:FREE Llama Models viaQroq
    • Open Router:ANY Other Models you can imagine!

// TODO: Rewrite Documentation

Model Pricing Table

ModelInput Cost per Million TokensOutput Cost per Million Tokens
gpt-4$30.00$60.00
gpt-4-turbo$10.00$30.00
gpt-4o$5.00$15.00
gpt-4o-mini$0.15$0.60
gpt-3.5-turbo-0125$0.50$1.50
claude-3-5-sonnet-20240620$3.00$15.00
claude-3-sonnet-20240229$3.00$15.00
claude-3-opus-20240229$15.00$75.00
claude-3-haiku-20240307$0.25$1.25
claude-2.1$8.00$24.00
claude-2.0$8.00$24.00
claude-instant-1.2$0.80$2.40
open-mistral-7b$0.25$0.25
open-mixtral-8x7b$0.70$0.70
open-mixtral-8x22b$2.00$6.00
mistral-small-2402$1.00$3.00
codestral-2405$1.00$3.00
mistral-medium-2312$2.70$8.10
mistral-large-2402$4.00$12.00
open-mistral-nemo$0.30$0.30
open-codestral-mamba$0.25$0.25

Free Models

The following models have no cost for input or output tokens:

  • gemini-pro
  • gemini-pro-vision
  • gemini-1.5-pro
  • gemini-1.5-flash
  • llama3-70b-8192
  • llama3-8b-8192
  • gemma-7b-it
  • mixtral-8x7b-32768

[8]ページ先頭

©2009-2025 Movatter.jp