ZH
2026 · Updated regularly

AI Coding Plans
Compared Side by Side

Claude Code · GLM · MiniMax · Kimi · Qwen
Pricing, models, usage limits, and supported tools — find the plan that fits your workflow

6
Platforms
$18
Lowest / mo
10+
AI Models
20+
Dev Tools

Quick Comparison

Entry-level plans at a glance — find your starting point

Scroll horizontally for full table
Platform Starting Price Core Models Usage (5h window) Tiers Highlight
Claude Code
 $20/mo Opus 4.6, Sonnet 4.6, Haiku 4.5 Usage limits apply 3 tiers Anthropic
GLM (Z.ai)
 $18/mo GLM-5.2, GLM-5-Turbo, GLM-4.7 10,000 Credits/week 3 tiers Free MCP Tools
MiniMax
 ¥49/mo MiniMax M3 · M2.7 · Multimodal 600M+ tokens/mo 3 tiers Token-Based
Kimi
 ¥49/mo Kimi K3 · K2.7 Code · High-Speed Weekly quota 4 tiers Waitlist
Qwen (Alibaba)
 ¥200/mo Qwen3.7-Plus, Qwen3.6-Plus, Kimi-K2.5, GLM-5, M2.5 6,000 requests 1 tier Limited stock
Xiaomi MiMo
 ¥39/mo MiMo-V2.5 Series · 6 models Credits-based, 0.8x off-peak 4 tiers OpenAI + Anthropic API

Detailed Plans

Deep dive into each platform's pricing and features

Claude Code Anthropic

Anthropic's flagship AI coding agent — terminal, IDE, web, and desktop
Models: Opus 4.6 · Sonnet 4.6 · Haiku 4.5
ProEntry
Includes Claude Code & Cowork Unlimited projects Memory across conversations
$20/mo
$17/mo billed annually
Max 5xPopular
5× Pro usage Higher output limits Priority access
$100/mo
Max 20xPower User
20× Pro usage Early access to features Priority at peak times
$200/mo
Available On
Terminal CLIVS CodeJetBrainsWebDesktop AppSlack
Opus 4.6 Extended Thinking Web Search Connectors / MCP
View Plans

GLM Coding Plan Free MCP

By Zhipu AI (Z.ai) — GLM-5.2 with a 1M-token context window
Models: GLM-5.2 · GLM-5-Turbo · GLM-4.7
LiteBudget
10,000 Credits / week Models and MCP tools consume Credits
$18/mo
$14.4/mo quarterly · $12.6/mo annual
Pro6× Lite
60,000 Credits / week For high-frequency complex projects
$80/mo
$64/mo quarterly · $56/mo annual
MaxMax Usage
140,000 Credits / week First access to new models · Priority access
$168/mo
$134.4/mo quarterly · $117.6/mo annual
Supported Tools
Claude CodeRoo CodeKilo CodeClineOpenCodeCrushGooseOpenClawCursor20+
Vision MCP Web Search MCP Web Reader MCP Zread MCP GLM-5.2 · 1M Context Referrers up to 20% Credits
Subscribe

MiniMax Token Plan M3

Three public tiers with M3, 1M context, native multimodal input, and shared Token-Based quotas
Models: MiniMax M3 · M2.7 · Image · Speech · Music
Current public tiers (official CNY pricing)
Plus
About 600M+ M3 tokens / month 3–4 concurrent agents
¥49/mo
¥490/yr
Max
About 1.8B+ M3 tokens / month 4–5 agents · 3 videos/day
¥119/mo
¥1,190/yr
UltraHeavy Use
About 7.1B+ M3 tokens / month 6–7 agents · 5 videos/day
¥469/mo
¥4,690/yr
Supported Tools
OpenClawClaude CodeRoo CodeKilo CodeClineCodex CLIOpenCodeCursorTRAEGrok CLI
M3 · 1M Context Shared Multimodal Quota Web Search MCP Invitee 10% Off · Referrer 10% Back
Subscribe

Kimi Code Plan Waitlist

All four published tiers currently show Join Waitlist; Agent Credits scale at base / 2× / 4× / 10×
Models: Kimi K3 · K2.7 Code · K2.7 Code High-Speed
AndanteDaily Use
Dedicated quota · Weekly refresh K2.7 Code · No K3 access
¥49/mo
Annual ¥39/mo (¥468/yr)
Moderato2× Credits
2× Agent Credits · 7-day refresh K3 256K · K2.7 Code Swarm: up to 2 subagents
¥99/mo
Annual ¥79/mo (¥948/yr)
Allegretto4× Credits
4× Agent Credits · K3 up to 1M · High-Speed Kimi Claw · Swarm: up to 4 subagents
¥199/mo
Annual ¥159/mo (¥1,908/yr)
Allegro10× Credits
10× Agent Credits · K3 up to 1M · High-Speed Kimi Claw · Swarm: up to 8 subagents Save ¥1,680/yr on annual plan
¥699/mo
Annual ¥559/mo (¥6,708/yr)
Supported Tools
Kimi CLIClaude CodeRoo CodeOpenCodeKimi Code for VS Code
Kimi K3 K2.7 Code / High-Speed Weekly Refresh Kimi Claw AI Website/Docs/PPT/Sheet Save up to ¥1,680/yr
Join Waitlist

Qwen Coding Plan Limited Stock

By Alibaba Cloud — Qwen series + third-party models. Pro tier only, limited daily stock — restocked at 09:30 BJT
Models: Qwen3.7-Plus · Qwen3.6-Plus · Kimi-K2.5
GLM-5 · MiniMax-M2.5
Qwen3-Coder-Next + 5 more
ProOnly Tier
6,000 requests / 5 hours 45,000 requests / week 90,000 requests / month
¥200/mo
Limited stock · restocked 09:30 BJT daily
⚠️ Model-call usage per interaction varies by tool, model, task, and context. Quotas apply across rolling 5-hour, weekly, and monthly windows. No refunds.
Quota Reset Rules
5h rolling refreshWeekly resetMonthly reset on billing date
Supported Tools
Qwen CodeQoderOpenClawOpenCodeClaude CodeCodexClineCursorKilo
Qwen3.7 / 3.6 Series Third-Party Models Limited Stock
Subscribe

Xiaomi MiMo Token Plan Claude + OAI API

MiMo-V2 is retired; all 6 V2.5 models included. Optional MiMo Claw add-on starts at ¥14.90 for the first month
Models: mimo-v2.5-pro · mimo-v2.5 · mimo-v2.5-asr
Three V2.5 TTS models (free for now)
LiteStarter
4.1B Credits / month Off-peak × 0.8 All 6 V2.5 models
¥39/mo
Annual ¥34.32/mo (¥411.84/yr)
StandardAdvanced
11B Credits / month Off-peak × 0.8 All 6 V2.5 models
¥99/mo
Annual ¥87.12/mo (¥1,045.44/yr)
ProBest
38B Credits / month Off-peak × 0.8 All 6 V2.5 models
¥329/mo
Annual ¥289.52/mo (¥3,474.24/yr)
MaxPower
82B Credits / month Off-peak × 0.8 All 6 V2.5 models
¥659/mo
Annual ¥579.92/mo (¥6,959.04/yr)
💡 Credits-based billing · Off-peak (0:00–8:00 BJT) consumption × 0.8 · First monthly purchase 12% off, then regular renewal · Annual 12% off · Friends get 10% off; referrers earn up to 20%
Supported Tools
Claude CodeOpenClawOpenCodeKilo CodeClineCodexCherry StudioQwen CodeMiMo Code
mimo-v2.5-pro Credits billing Off-peak 0.8× OpenAI + Anthropic API Free TTS MiMo Claw Add-on
Subscribe Now

Frequently Asked Questions

Common questions about AI Coding Plans

What is a Coding Plan?
A Coding Plan is a monthly, quarterly, or annual AI coding subscription. It provides the platform's stated token, Credit, request, or rolling-window allowance for supported coding tools. Units, rate limits, and overage behavior differ by platform; these plans are not unlimited.
Which coding tools are supported?
Most plans support Claude Code, Cursor, Cline, Roo Code, Kilo Code, and OpenCode. GLM and MiniMax support 10–20+ tools. Kimi works primarily through Kimi CLI, Claude Code, and Roo Code. Claude Code's own plan works across terminal, VS Code, JetBrains, web, and desktop.
What does "5-hour rolling limit" mean?
Some platforms use a rolling or fixed 5-hour window. MiniMax now uses Token-Based quotas with a fixed 5-hour window and an additional weekly window; its published M2.7 request counts are reference estimates, not hard plan limits.
How many model calls does one prompt use?
A single interaction can trigger multiple model calls, depending on the tool, model, task, and context. This site does not assume one universal multiplier; use your own observed average when estimating request-based plans.
How should I compare plan value?
Filter by budget, tool compatibility, and current availability first. Then compare each platform's own token, Credit, request, or rolling-window allowance. These units are not interchangeable without evidence.
Can I get a refund?
Refund policies vary by platform. Most subscriptions are non-refundable once activated. We recommend starting with a lower tier to test the service before committing to a higher plan.