Skip to main content
Chinese AI Tools
ProductsModelsIntegrationsRankingsLatest changes
TopicsAvailability TrackerUse casesSubmit a toolAccount
ZHSearch

Chinese AI Tools

Independent directory for Chinese AI products. Product availability, pricing and terms can change. Verify before commercial use.

Editorial standardsClaim productUpdate infoGet featuredAdvertise

Zhipu AI

GLM Coding Plan

Z.ai's subscription quota for GLM coding models across Claude Code, OpenClaw and more than 20 supported developer tools.

Globally availableFull English UIPublic APIPaid

Quick answer

GLM Coding Plan has its own prices, endpoints, supported-tool policy, quotas and MCP allowances, so it should be tracked separately from the BigModel API and z.ai assistant.

Official sitePricingDocumentation
Pricing
Standard monthly: Lite $18, Pro $72, Max $160; annual billing shown as $12.60, $50.40 and $112 per month
Availability
Globally available
API
Public API
Last checked
2026-08-14
Pricing detailsUse-case fitSource evidence

GLM Coding Plan is Z.ai's subscription route for coding agents and IDE tools. All tiers now support GLM-5.3, GLM-5-Turbo and GLM-4.7; requests using the previous GLM-5.2 or GLM-5.1 IDs are automatically routed to GLM-5.3. The plan uses points calculated separately from input, cached-input and output tokens, with Lite, Pro and Max receiving 2,000/10,000, 12,000/60,000 and 28,000/140,000 five-hour/weekly credits. Off-peak model usage costs 50% of standard credits. The plan integrates with more than 20 tools and includes Vision Understanding, Web Search, Web Reader and Zread MCP services.

Topic guide

GLM models, Coding Plan and Z.ai ecosystem

A source-backed map of the original GLM-5.3, open multimodal GLM-5.3-Flash, GLM-5.2, BigModel APIs, Coding Plan, ZCode, consumer agents and media products.

Editorial verdict

Best for

Developers who want predictable GLM usage for supported coding agents, repository work and MCP-assisted research.

Avoid if

Avoid it when you need a general-purpose API quota, unsupported tools, refundable billing or throughput without rolling and weekly caps.

Why it matters

GLM Coding Plan has its own prices, endpoints, supported-tool policy, quotas and MCP allowances, so it should be tracked separately from the BigModel API and z.ai assistant.

Trust: 4/4 sources verified, recently checkedCoverage: 100/100

Pricing

Standard monthly: Lite $18, Pro $72, Max $160; annual billing shown as $12.60, $50.40 and $112 per month

Payment

Z.ai credits, Cash balance, Bank card, PayPal, Auto-renewing subscription

Commercial use

Commercial use should follow the current product, API, model license and billing terms.

Privacy

Review prompt, file, media upload, retention and training-use terms before sensitive workloads.

Use-case fit

Claude Code with GLM

Strong

Use the documented Anthropic-compatible endpoint and map Claude model variables to GLM models.

OpenClaw and coding agents

Strong

Use the plan with officially supported agent tools sharing one subscription quota.

MCP-assisted development research

Strong

Use Vision Understanding, Web Search, Web Reader and Zread MCP alongside coding sessions.

Tiered repository workloads

Medium

Choose among 2,000, 12,000 or 28,000 five-hour credits and corresponding 10,000, 60,000 or 140,000 weekly caps based on repository workload.

Global user checklist

RegistrationConfirmedThe English subscription page exposes Lite, Pro and Max purchase and account-management flows.
English UIConfirmedSubscription, FAQ, integration and policy documentation are English-facing.
API and docsConfirmedDocs publish dedicated endpoints, model mappings, supported tools, MCP setup and Coding Tool Helper instructions.
International paymentReviewBilling auto-renews, subscriptions are non-refundable and cancellation should be completed at least 24 hours before renewal.
Commercial usePartialUse is restricted to officially supported tools and products; review the usage policy before team automation.
Data and privacy termsReviewRepository content, visual input, web results and tool traces may be sent through Z.ai models and MCP services.

Checked on August 14, 2026. GLM-5.3 is available to all Coding Plan users under the new points system. Previous GLM-5.2 and GLM-5.1 IDs are automatically routed to GLM-5.3. Verify live prices, credit multipliers, five-hour and weekly caps, promotions and MCP quotas before purchase.

Pros

  • - Supports GLM-5.3, GLM-5-Turbo and GLM-4.7 on every tier
  • - Works with more than 20 coding tools, including Claude Code and OpenClaw
  • - Dedicated coding endpoints prevent plan calls from consuming ordinary API balance
  • - All tiers include Vision Understanding, Web Search, Web Reader and Zread MCP access
  • - Off-peak model usage is charged at 50% of standard credits outside weekday 14:00-18:00 UTC+8

Cons

  • - Subscription benefits are strictly limited to officially supported tools and scenarios
  • - A weekly credit quota applies in addition to the rolling five-hour credit limit
  • - GLM-5.3 has the highest listed token multipliers: 6.9 input, 1.7 cached input and 24 output credits per 10,000 tokens
  • - Subscriptions auto-renew and are non-refundable after purchase
  • - Plan quota cannot be used for arbitrary API calls outside supported coding tools

Decision paths

qwen-cloud-token-plan

step-plan

minimax-token-plan

opencode-go

Sources

GLM-5.3 official release

Official · EN · verified 2026-08-14

Confirms GLM-5.3 availability for all Coding Plan users, low/high/max effort, points-based usage and the 50% off-peak rate.

GLM Coding Plan overview

Documentation · EN · verified 2026-08-14

Confirms supported models, automatic routing from older IDs, five-hour and weekly credits, token multipliers, off-peak pricing and estimated weekly token ranges.

GLM Coding Plan subscription

Pricing · EN · verified 2026-06-13

Confirms Lite, Pro and Max prices, annual discounts, plan positioning, supported-tool breadth and MCP inclusion.

GLM Coding Plan FAQ

Documentation · EN · verified 2026-08-14

Documents billing, refunds, endpoint restrictions and subscription usage rules that remain separate from ordinary API balance.

Last checked: 2026-08-14

Reviews

No approved reviews yet.

Availability snapshot

Availability
Globally available
English UI
Full English UI
API
Public API
Rating
4.4 (0)

Latest updates

Latest changes
Open source · 2026-08-28

GLM-5.3-Flash adds open weights, API and multimodality

Z.AI released GLM-5.3-Flash under MIT with first-party API and local deployment paths. The natively multimodal model uses 320B total and 18B active parameters, a 1M context configuration, hybrid sparse and linear attention, and low, high or max reasoning effort. Existing GLM selection and Kimi comparison content now distinguishes this variant from the original text-only GLM-5.3 launch.

Release · 2026-08-14

Z.ai releases GLM-5.3 to Coding Plan users

At the original August 14 launch, Z.ai released GLM-5.3 for Coding Plan users using the same base model as GLM-5.2 with scaled post-training. The vendor reported stronger long-horizon coding and cybersecurity results, required thinking with low, high or max effort, and described general API access and weights as future work. The later GLM-5.3-Flash release is tracked separately.

Market · 2026-06-21

GLM-5.2 reported at No. 1 on Design Arena

GizmoChina reports that GLM-5.2 took the top position on the crowdsourced web-design benchmark Design Arena ahead of Claude Fable 5. VentureBeat separately cites a 1360 ELO score. This is recorded as a media-reported arena result, not an independently reproduced evaluation, and rankings may change as new votes and models are added.

Market · 2026-06-21

VentureBeat compares GLM-5.2 cost with proprietary frontier models

VentureBeat reports GLM-5.2 API rates of $1.40 per million input tokens, $4.40 per million output tokens and $0.26 per million cached-input tokens. Its 'one-sixth the cost' headline compares the $5.80 input-plus-output total with GPT-5.5's listed $35 total; real savings depend on workload token mix, caching and provider terms. The article's benchmark comparisons largely reproduce Z.ai's vendor-reported results.

Submit a review