Z.AI is the July best value coding subscription to test when supported tools fit. The current headline is the GLM Coding Plan, starting at $18/month, with GLM-5.2 as the current flagship coding model and an invite program whose official rules still list a first-order GLM Coding discount.

It is not a universal replacement for GPT or Claude. The useful claim is narrower: GLM-5.2 is a credible low-cost coding and agent model to test at a much lower subscription price than running every coding loop through a premium Western API. Keep Claude Opus 4.8 for final arbitration until GLM passes your own repo tasks.

Start here: Subscribe through Z.AI

What You Get

The GLM Coding Plan is a subscription package for AI-powered coding, not a general unlimited API plan. Z.AI documents support for coding tools including Claude Code, OpenCode, Cursor, Cline, TRAE, Qoder, Droid, Kilo Code, Roo Code, Crush, Goose, and Eigent. OpenClaw is documented separately as a supported general-agent path with best-effort scheduling. Subscription usage is limited to officially supported tools, products, and endpoints.

Supported plan models currently include:

ModelPractical role
GLM-5.2Complex coding, long-horizon work, harder agent loops
GLM-5-TurboAdvanced coding model with similar quota treatment
GLM-4.7Routine development, Sonnet-style default lane
GLM-4.5-AirLightweight work and cheaper/faster routing

The important operational detail: Z.AI says GLM Coding Plan quota only applies in supported tools and products. API or SDK usage outside the Coding Plan path can be restricted or billed differently.

Why This Plan Is On The Value Shortlist

The plan is useful because it gives you a paid coding lane that is cheaper than keeping every agent loop on GPT or Claude API pricing. It is not free, and it is not unrestricted. The value case is:

Buyer questionZ.AI answerCaveat
“Can I run Claude Code-style workflows cheaper?”Yes, if your tool is supported and GLM-5.2 is good enough for your repo.Unsupported tools and direct SDK/API usage do not get Coding Plan quota.
“Is GLM-5.2 the model to use all day?”Use it for harder planning, refactors, and stuck bugs.It can burn quota faster than GLM-4.7 or GLM-4.5-Air.
“Is this a replacement for Opus or GPT?”It can replace many low-risk coding loops if it passes your evals.Keep Opus 4.8 or GPT for high-risk changes and final arbitration.
“Is the invite discount guaranteed?”Official campaign rules currently list 5% for eligible first GLM Coding orders.Checkout controls the real price before payment.

Pricing And Quotas

Z.AI’s public docs list GLM-5.2 API pricing at $1.40 per 1M input tokens, $0.26 per 1M cached input tokens, and $4.40 per 1M output tokens. Against Claude Opus 4.8 API list pricing, that is about 72% lower input and 82.4% lower output. The Coding Plan is different: it bundles supported-tool usage behind subscription quotas.

Plan5-hour estimateWeekly estimateBest fit
LiteUp to ~80 promptsUp to ~400 promptsOne project at a time
ProUp to ~400 promptsUp to ~2,000 prompts1-2 active projects
MaxUp to ~1,600 promptsUp to ~8,000 promptsHeavy or parallel coding work

Z.AI says each prompt is estimated to invoke the model 15-20 times, and actual usage varies by repository size, task complexity, and auto-accept behavior.

For a first test, Lite is the cleanest sanity check: wire it into one supported coding tool, run it against real repo tasks, and decide whether the model saves enough Claude/GPT spend to justify upgrading. Pro and Max only make sense after you have evidence that GLM handles your codebase well.

The GLM-5.2 Quota Caveat

GLM-5.2 and adjacent advanced GLM models should be treated as quota-sensitive lanes. Z.AI’s Coding Plan docs can change quota multipliers by model and hour, so check the current plan page before routing every prompt to the flagship model.

The practical routing rule is simple: use GLM-5.2 for hard planning, architecture, large refactors, and stuck bugs. Keep routine edits on cheaper GLM lanes where available so the subscription does not burn down early. Artificial Analysis flags output-token efficiency as a caveat, so track total tokens and retries instead of assuming raw input price tells the whole story.

Tool Setup

Use the Coding Plan endpoint for OpenAI-compatible coding tools:

1

https://api.z.ai/api/coding/paas/v4

Use the Anthropic-compatible endpoint for Claude Code and Goose:

1

https://api.z.ai/api/anthropic

For Claude Code, Z.AI’s example maps:

1
2
3
4
5
6
7
8
9

{
  "env": {
    "ANTHROPIC_AUTH_TOKEN": "your_Z.ai_api_key",
    "ANTHROPIC_BASE_URL": "https://api.z.ai/api/anthropic",
    "ANTHROPIC_DEFAULT_OPUS_MODEL": "glm-5.2",
    "ANTHROPIC_DEFAULT_SONNET_MODEL": "glm-4.7",
    "ANTHROPIC_DEFAULT_HAIKU_MODEL": "glm-4.5-air"
  }
}

That split matches the cost-control pattern: GLM-5.2 for Opus-grade work, GLM-4.7 for routine development, GLM-4.5-Air for light tasks.

Deployment Eval

Do not buy the plan from a benchmark headline alone. Use public numbers as a shortlist signal, then run GLM-5.2 against one real repository task before making it your daily lane.

Current public signals are strong enough to test:

SourceSignalCaveat
Artificial AnalysisIntelligence Index 51, GDPval-AA v2 1524, leading open-weights placementIndependent benchmark signal, not your repo
Z.AISWE-Bench Pro 62.1 and Terminal-Bench 2.1 81.0Vendor-published coding signal
AIHackersNo owned GLM-5.2 eval yetRun the deployment eval below
Eval stepWhat to comparePass signal
Real bugAsk GLM-5.2 and your premium fallback to fix the same failing testGLM produces the smaller correct patch or a clearly usable diagnosis
RefactorGive both models a 2-4 file cleanup with existing project conventionsGLM preserves behavior and avoids unrelated churn
Test behaviorRequire the coding tool to run or explain the relevant testsGLM uses the repo’s test path instead of guessing
ReviewHave GLM review the premium model’s patch, then reverse the orderFindings are concrete, file-grounded, and not invented

If GLM-5.2 handles those tasks well enough, use it for routine coding loops. Keep GPT or Claude for risky migrations, final arbitration, and places where a wrong patch costs more than the subscription savings.

When To Choose Z.AI

Choose Z.AI when:

  • You want a cheaper supported-tool lane for daily coding.
  • You use Claude Code, OpenCode, Cursor, Cline, TRAE, Qoder, Droid, Kilo Code, Roo Code, Crush, Goose, Eigent, or the documented OpenClaw path and can stay inside supported tool paths.
  • You want subscription-style budgeting instead of every coding loop hitting a full-price API key.
  • You are comfortable with quota management and model routing.

Skip Z.AI when:

  • You need the single strongest coding model regardless of cost. Use Claude Opus 4.8 or GPT-5.5 for that lane.
  • You need an unrestricted general API subscription. The Coding Plan is restricted to supported tools.
  • You cannot tolerate non-refundable subscription terms or automatic renewal.
  • You do not want to manage peak-hour and weekly quota behavior.

GLM-5.2 In Context

LaneAPI input/outputContextWhy you would choose it
GLM-5.2 / Z.AI$1.40 / $4.401MLow-cost supported-tool coding subscription, good candidate for long-context repo loops
Kimi K3$0.30 cache-hit / $3.00 cache-miss input, $15.00 output1MNewest Kimi flagship to test when Kimi is already in your stack
Kimi K2.7 Code$0.19 cache-hit / $0.95 cache-miss input, $4.00 output256K-classCheaper routine Kimi coding API path
OpenAI GPT-5.xPremium API lane1M-classOpenAI-native workflows, broad tool ecosystem, premium arbitration
Claude Opus 4.8 / SonnetOpus $5 / $25; Sonnet $3 / $151M-classHighest-confidence coding reviews, architecture, and complex agent work

GLM-5.2’s own docs publish stronger long-horizon coding claims and position it for project-scale engineering context. Treat that as vendor-published directional evidence, not purchase proof or a guarantee that it beats Opus or GPT in your repo.

Buyer Checklist

Before you subscribe:

  • Confirm the checkout page still shows the expected first-order discount.
  • Confirm your target tool is on Z.AI’s supported-tool list.
  • Decide which model gets each role: GLM-5.2 for hard work, GLM-4.7 for routine edits, GLM-4.5-Air for light tasks.
  • Run one deployment eval against a real repo task before changing your primary coding lane.
  • Keep one premium fallback, such as Claude Opus 4.8, available until GLM-5.2 has passed your own repo eval.
  • Recheck renewal, refund, and weekly quota behavior before choosing annual billing.

Bottom Line

Z.AI is currently the clearest low-cost coding subscription to test when your workflow fits its supported tools. The trade is straightforward: lower cost and broad tool compatibility in exchange for supported-tool restrictions, quota accounting, and subscription rules. Official invite rules currently list a 5% first-order GLM Coding discount for eligible invited users, but verify the final amount at checkout before paying.

CTA: Try the Z.AI GLM Coding Plan

Sources

Last verified: July 2, 2026. Recheck pricing, quota multipliers, supported tools, benchmark positions, and referral discount text at checkout before purchasing.