Skip to content

Releases: D3-vin/Verdent2Api

Verdent 2API v1.0.1 - Bug Fixes

Choose a tag to compare

@D3-vin D3-vin released this 04 Sep 18:52

Verdent 2API v1.0.1 - Bug Fixes

Minor improvements and bug fixes.

🐛 Bug Fixes

  • Documentation updates — Fixed typos and improved clarity
  • Build improvements — Optimized build configuration
  • Minor stability fixes — General code improvements

📥 Downloads

Main Binary

Platform Download Size
Windows x64 verdent-windows-amd64.exe ~7.3 MB
Linux x64 verdent-linux-amd64 ~7.1 MB
macOS Intel verdent-macos-amd64 ~7.2 MB
macOS Apple Silicon verdent-macos-arm64 ~6.7 MB

🚀 Quick Start

# Download and run
./verdent-*

# Dashboard: http://localhost:5084
# API: http://localhost:5084/v1/chat/completions

🔧 IDE Configuration

Base URL: http://localhost:5084/v1
API Key: change-me
Model: deepseek-v4-flash-free

📝 Changelog

Full Changelog: v1.0.0...v1.0.1


📖 Documentation

📱 Contact

Verdent 2API v1.0.0 - Initial Public Release

Choose a tag to compare

@D3-vin D3-vin released this 04 Sep 18:33

Verdent 2API v1.0.0 - Initial Public Release

First public release of Verdent 2API — OpenAI & Anthropic-compatible proxy for Verdent.ai.

🚀 What's New

  • OpenAI & Anthropic compatibility — Full support for /v1/chat/completions and /v1/messages endpoints
  • Tool calling support — Complete function calling implementation for IDE integration
  • Multi-account pooling — JWT rotation with automatic failover and quota tracking
  • Embedded dashboard — Web UI for account management and OAuth login at http://localhost:5084
  • Cross-platform — Single Go binary for Windows, macOS (Intel/ARM), and Linux

📥 Downloads

Main Binary

Platform Download Size
Windows x64 verdent-windows-amd64.exe ~7.3 MB
Linux x64 verdent-linux-amd64 ~7.1 MB
macOS Intel verdent-macos-amd64 ~7.2 MB
macOS Apple Silicon verdent-macos-arm64 ~6.7 MB

🚀 Quick Start

# Download and run
./verdent-*

# Dashboard: http://localhost:5084
# API: http://localhost:5084/v1/chat/completions

🔧 IDE Configuration

Base URL: http://localhost:5084/v1
API Key: change-me
Model: deepseek-v4-flash-free

Works out of the box with AI coding assistants!

📝 Available Models

  • deepseek-v4-flash-free — Fast and efficient (300K-1M context)
  • glm-5.3-flash-free — Balanced performance (300K-1M context)

Both models support:

  • Streaming chat
  • Tool calling (function calling)
  • Deep thinking mode
  • Web search integration

📖 Documentation

📱 Contact