Skip to content

GLM Coding Plan With Claude Code: Current Setup

Set up Z.AI's GLM Coding Plan with Claude Code using GLM-5.3, the Anthropic-compatible endpoint, and current points-based usage rules.

MGMCSA Guru Team August 16, 2026 2 min read
GLM Coding Plan configured with Claude Code

Z.AI’s Coding Plan can power Claude Code through an Anthropic-compatible endpoint. The current model is glm-5.3. Older setup guides that select GLM-5.1 or GLM-5-Turbo should be migrated.

What the plan covers

The subscription uses a points quota instead of an unlimited request allowance. The number of points used depends on the model and traffic period. Z.AI currently applies a half-points rate during its published off-peak window, so read the live plan page before choosing a tier.

Current setup values

Model glm-5.3
Protocol Anthropic-compatible
Base URL https://api.z.ai/api/anthropic
Input Text
Context Up to 1 million tokens

Configure Claude Code

In a Linux or WSL shell, set the variables for the current session:

export ANTHROPIC_BASE_URL="https://api.z.ai/api/anthropic"
export ANTHROPIC_AUTH_TOKEN="your-zai-plan-key"
export ANTHROPIC_MODEL="glm-5.3"
claude

In PowerShell, use the equivalent $env:NAME = "value" form. Store the key in a secure user-level secret or shell configuration that is excluded from source control.

Control usage

Use low reasoning effort for routine edits when the client supports it. Move to high or max for difficult debugging. GLM-5.3 always reasons, so effort changes the amount of work rather than turning reasoning off.

Keep an eye on the points balance when Claude Code runs long agent loops. A plan makes billing predictable, but unattended retries can still exhaust its quota.

Troubleshooting

  • A 401 response usually means the key is missing or invalid.
  • A 404 or format error usually means the wrong protocol endpoint was copied.
  • A model error usually means an older or misspelled ID is configured. Use glm-5.3.
  • An image task will not work as expected because GLM-5.3 accepts text input.

GLM Coding Plan checklist

  • Coding Plan activated and key created
  • Anthropic-compatible endpoint configured
  • Model set to glm-5.3
  • Key kept outside the repository
  • Points usage checked after a test task

For a fuller Windows walkthrough, see GLM-5.3 with Claude Code. For editor use, see GLM-5.3 with Cline.

Frequently asked questions

Does the GLM Coding Plan work with Claude Code?

Yes. Z.AI provides an Anthropic-compatible endpoint at https://api.z.ai/api/anthropic. Set that URL, your plan key, and glm-5.3 in Claude Code.

Is the GLM Coding Plan unlimited?

No. Current plans use points quotas. Model choice and traffic period affect consumption, and Z.AI currently charges half points during its published off-peak period.

Which model should I use?

Use glm-5.3 for a new setup. Z.AI lists it for all Coding Plan users and documents a 1 million-token context window.

Does GLM-5.3 support screenshots?

No. It is a text-input model. Send source files, logs, and text prompts instead.

Sources & further reading

Official vendor documentation referenced while writing this guide.

MG

MCSA Guru Team

IT & Systems Administration

We are working IT pros and system administrators who spend our days in Windows Server, Microsoft 365, and the wider Microsoft stack. MCSA Guru is where we write down the fixes and walkthroughs we wish we had found the first time.

MCSA Guru provides independent, educational IT guidance. Microsoft, Windows, Windows Server, Microsoft 365, Exchange, and Microsoft Teams are trademarks of Microsoft Corporation; Docker is a trademark of Docker, Inc. MCSA Guru is not affiliated with or endorsed by Microsoft or Docker. Always test changes in a safe environment before applying them in production.

Related guides

Fixing something right now?

Jump straight into the guide library or search for the exact error or task you are dealing with.