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

5
Platforms
$10
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 Claude Opus 4.7, Sonnet 4.6 Usage limits apply 3 tiers Gold Standard
GLM (Z.ai)
$18/mo GLM-5.2, GLM-5.1, GLM-5-Turbo, GLM-5, GLM-4.7 ~80 prompts 3 tiers Free MCP Tools
MiniMax
$10/mo M3, M2.7, M2.7-highspeed 100 prompts 6 tiers 100+ TPS
Kimi
~$7/mo Kimi K3 · K2.6 300–1,200 calls 5 tiers K3 New
Qwen (Alibaba)
$50/mo Qwen3.5-Plus, GLM-5, Kimi 6,000 requests 1 tier Limited Restock

Detailed Plans

Deep dive into each platform's pricing and features

Claude Code Gold Standard

Anthropic's flagship AI assistant — Opus 4.7 programming powerhouse, terminal, IDE, web, and desktop
Models: Claude Opus 4.7 · Sonnet 4.6
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

GLM Coding Plan GLM-5.2

By Zhipu AI (Z.ai) — GLM-5.2 fully available, 1M context, #1 open-source & #2 global on LMArena Code · Weekly Credits
Models: GLM-5.2 · GLM-5.1 · GLM-5-Turbo · GLM-5 · GLM-4.7
LiteBudget
10,000 Credits / week Gradual access to latest flagship ZCode / Claude Code / 20+ tools
$18/mo
Yearly $12.6/mo (-30%)
ProBest Value
6× Lite usage (~60,000 credits/week) Priority flagship access Curated MCP tools · Faster generation
$80/mo
Yearly $56/mo (-30%)
MaxFlagship Access
14× Lite usage (~140,000 credits/week) First access to new models Peak-hour priority
$168/mo
Yearly $117.6/mo (-30%)
Supported Tools
ZCodeClaude CodeCursorOpenClawOpenCodeClineRoo CodeKilo CodeCrushFactory20+

MiniMax Token Plan M3 Model

M3 flagship — frontier coding, 1M context, native multimodal, 2 months free on annual plans
Models: M3 · M2.7 · M2.7-highspeed
Standard Plans (M2.7 ~50 TPS)
StarterEntry
100 prompts / 5 hours Lightweight workloads
$10/mo
$100/yr (save $20)
Plus
300 prompts / 5 hours 3× Starter usage
$20/mo
$200/yr (save $40)
Max
1,000 prompts / 5 hours 10× Starter usage
$50/mo
$500/yr (save $100)
High-Speed Plans (M2.7-highspeed ~100 TPS)
Plus HS
300 prompts / 5 hours ~100 TPS high-speed inference
$40/mo
$400/yr (save $80)
Max HSTop Pick
1,000 prompts / 5 hours ~100 TPS high-speed inference
$80/mo
$800/yr (save $160)
Ultra HSFastest
2,000 prompts / 5 hours 20× Starter usage
$150/mo
$1,500/yr (save $300)
Supported Tools
Claude CodeRoo CodeKilo CodeClineCodex CLIOpenCodeCursorTRAEGrok CLI

Kimi Code Plan K3 New Model

By Moonshot AI — Kimi K3 flagship (2.8T parameters, released 2026/7/17) + K2.6 across five tiers; Moderato+ unlocks K3 and Allegro unlocks 1M-token conversations
Models: Kimi K3 · K2.6
AdagioFree
Kimi K2.6 / K2 access 1 concurrent Agent task 2 projects · 500 MB storage K3 requires Moderato or above
¥0/mo
Free starter tier
AndanteBasic
Approx. 300–1,200 API calls / 5h Quota refreshes every 7 days Kimi K2.6 flagship access K3 requires Moderato or above
¥49/mo
Annual: ¥39/mo (¥468/year)
ModeratoRecommended · K3
Larger quota · refreshes every 7 days Kimi K3 flagship (2.8T parameters) 2 concurrent Agent tasks · 2 cluster subtasks Claude Code / Roo Code support
¥99/mo
Annual: ¥79/mo (¥948/year)
AllegrettoAdvanced · K3
Larger quota · Agent cluster 40 times/mo 2 concurrent Agent tasks · 4 cluster subtasks Goal Mode · 10 Kimi Claw group chats Priority generation queue
¥199/mo
Annual: ¥159/mo (¥1,908/year)
AllegroTop · 1M Context
K3 with 1M-token conversation capacity 4 concurrent Agent tasks · 8 cluster subtasks 10 Kimi Claw group chats Goal Mode · Cloud / Android / Desktop
¥699/mo
Annual: ¥559/mo (¥6,708/year)
Quotas refresh every 7 days and do not roll over · Maximum concurrency: 30 · K3 is available on Moderato and above · Allegro exclusively unlocks 1M-token conversations
Supported Tools
Kimi CLIClaude CodeRoo CodeKimi Code for VS Code

Qwen Coding Plan Limited Restock

By Alibaba Cloud — Lite discontinued, only Pro remains with daily limited restock at 9:30 AM
Models: Qwen3.5-Plus · Qwen3-Max
Qwen3-Coder-Next · Qwen3-Coder-Plus
GLM-5 · GLM-4.7
Kimi-K2.5 · MiniMax-M2.5
LiteDiscontinued
1,200 requests / 5 hours 18,000 requests / month New purchases stopped Mar 20
$10/mo
Discontinued
ProOnly Tier Left
6,000 requests / 5 hours 45,000 requests / week 90,000 requests / month
$50/mo
Daily limited restock at 9:30 AM
⚠️ Lite plan discontinued · Pro restocked daily in limited quantities, usually sells out within minutes
Quota Reset Rules
5h rolling refreshWeekly resetMonthly reset on billing date

Frequently Asked Questions

Common questions about AI Coding Plans

What is a Coding Plan?
A Coding Plan is a monthly subscription offered by various AI platforms that gives you access to their models inside coding tools like Claude Code, Cursor, Cline, and more. Instead of paying per token, you pay a flat fee and get a generous usage quota that refreshes on a rolling basis. Note: Alibaba Cloud Lite has been discontinued, and Coding Plans are becoming increasingly scarce.
Which coding tools are supported?
Most plans support Claude Code, Cursor, Cline, Roo Code, Kilo Code, OpenCode, OpenClaw and ZCode. 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 the 5-hour rolling limit mean?
Older plans used a rolling 5-hour window. The new GLM Coding Plan now uses weekly Credits that refresh every 7 days (Lite: 10,000 credits/week, Pro: 6× Lite, Max: 14× Lite). Other providers (Kimi Code, MiniMax M2.7) still enforce a 5-hour window.
What is the latest GLM Coding Plan pricing?
GLM Coding Plan now charges Lite $18/mo ($12.6/mo yearly), Pro $80/mo ($56/mo yearly), Max $168/mo ($117.6/mo yearly). Quarterly billing gives 20% off and yearly billing 30% off. Lite ships with 10,000 weekly Credits, Pro is 6× Lite, and Max is 14× Lite.
How many model calls does one prompt use?
In coding tools, a single user prompt typically triggers 5–30 model calls behind the scenes, as the tool performs code analysis, search, generation, and validation steps. Different platforms count usage differently — some count "prompts" (user messages), others count raw API requests. Check each platform's docs for specifics.
Which plan offers the best value?
It depends on your needs. For a low entry price, GLM Lite at $18/mo (~$12.6/mo yearly) is the strongest contender. For a balance of price and performance, MiniMax Plus gives you 6B+ tokens with the M3 flagship model. For the best model quality, Claude Code Pro at $20/month gives you access to Claude Opus 4.7. For multi-model flexibility, Qwen's plan lets you switch between 8+ models (Pro only, limited restock).
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.
Mobile Coding · New

Got your Coding Plan?
Code on mobile with kkcode.app

kkcode.app is the mobile client for OpenCode. Connect your Coding Plan subscription and keep coding on the go — commute, breaks, or when inspiration strikes.

Works with Coding Plans OpenCode on Mobile iOS / Android Multi-model
Learn more →
⌨️
kkcode.app
📱 💻