Tencent Marvis vs Astron Coding Plan

Compare Tencent Marvis and Astron Coding Plan: free credits, features, and ratings. Which one is right for you?

Category
AI Assistant
Coding Assistant
Rating
⭐ 3.5
⭐ 3
Free Credits
1000 undefined
3.9 undefined
Refresh Period
daily
monthly
Resolution
N/A
N/A
Watermark
No
No
Commercial Use
No
No
Paid From
Completely free
First purchase Β₯3.9/month, renewal Β₯19/month

Tencent Marvis

Operating system-level AI assistant by Tencent's App Store team. Fully launched May 21. 10M free tokens daily, powered by DeepSeek V4 and Hunyuan models. Windows, Mac, Android. Privacy mode (local model, zero upload) and efficiency mode (cloud-edge). 8 built-in agents for file search, system settings, remote control, document processing.

Pros

  • βœ“Completely free, 10M tokens daily
  • βœ“OS-level agent, truly controls PC
  • βœ“Privacy mode, zero file upload
  • βœ“Phone remote control of PC
  • βœ“8 built-in agents, ready to use
  • βœ“DeepSeek V4 + Hunyuan dual models

Cons

  • βœ—Requires 16GB RAM minimum
  • βœ—Mac needs M1 or newer
  • βœ—iOS not yet available (mid-June)
  • βœ—Tencent ecosystem lock-in risk

Key Features

OS-level AI AgentLocal file smart searchOne-sentence PC settingsPhone remote control PCDeep file understandingPrivacy mode (local model)8 built-in specialized agentsWindows/Mac/Android
View Details β†’

Astron Coding Plan

Astron Coding Plan by iFlytek is a monthly AI coding subscription service for developers, integrating Spark X2, GLM, Kimi, MiniMax, DeepSeek, Qwen and other popular open-source models. First purchase only Β₯3.9/month with unlimited requests.

Pros

  • βœ“Ultra-low price: First purchase Β₯3.9/month, renewal Β₯19/month
  • βœ“Unlimited requests: Worry-free plan has no call limits
  • βœ“Rich model support: DeepSeek V3.2, Qwen3.5, GLM-5 and more
  • βœ“Good compatibility: Supports mainstream coding tools and standard protocols

Cons

  • βœ—Β₯3.9 is first purchase price only, renewal is Β₯19/month
  • βœ—Only for coding tools, cannot be used for automation scripts or backend services
  • βœ—Rate limits apply, may trigger throttling during peak hours
  • βœ—Advanced models (GLM-5, Kimi-K2.5 etc.) only available in Professional plan and above

Key Features

First purchase only Β₯3.9/month, extremely cost-effectiveUnlimited requests, enjoy monthlySupports 6+ popular open-source models (DeepSeek, Qwen, GLM, Kimi, MiniMax)Compatible with Claude Code, Cursor, OpenClaw, OpenCode and other coding toolsSupports OpenAI and Anthropic protocol accessProfessional and Premium plans offer more models and higher concurrency
View Details β†’