---
title: "ZCode coding plan: base URL & API key setup"
description: "The ZCode desktop IDE on a coding plan from $10/mo: Anthropic and OpenAI base URLs with one API key for Sonnet 5.5, Opus 5.5 and GLM. No surprise charges."
url: https://codingpass.ai/tools/zcode
language: en
updated: 2026-11-17
---
# The coding plan for ZCode.

Keep ZCode as it is. Switch a provider to API Key mode with CodingPass’s Anthropic and OpenAI base URLs, and run Claude Sonnet 5.5, Opus 5.5 and GLM on one monthly coding plan.

- Setup in 60s
- No surprise charges
- Full refund if you've used 5% or less

ZCode model settings

```
OpenAI Base URL     https://codingpass.ai/v1
Anthropic Base URL  https://codingpass.ai
API Key             cp-live-…
Model               claude-sonnet-5-5
```

Model ID for your plan

**Go**

claude-sonnet-5-5

**Plus**

claude-opus-5-5

**Pro**

claude-fable-5-2

## A desktop agent that checks its own work.

Z.ai's coding agent, built around GLM. All of it runs on CodingPass.

### The desktop agent for GLM

Z.ai's official desktop app for coding with GLM. One workspace per task: chat, terminal, Git changes and review in one window.

### Checks its own front-end work

The agent drives a built-in browser: it opens your dev server, clicks through, takes screenshots and checks the result instead of telling you it should be fine.

### Open source under Apache-2.0

Z.ai publishes ZCode's source on GitHub under Apache-2.0. You can read it, build it yourself or fork it.

### Long tasks, steered from your phone

Files, terminal output and Git state stay with the task from plan to verification. Remote on mobile, or a Feishu or WeChat bot, keeps it moving while you are away.

## Which plan for ZCode?

Every plan works with ZCode. Pick the Claude flagship you want as your default; all open-weight models, GLM included, come with every plan and share the same monthly allowance.

- [Full plan details](https://codingpass.ai/pricing#compare-plans)
- [Allowances for all 24 models](https://codingpass.ai/models)

### Go: Claude Sonnet 5.5

Best for Daily coding, with GLM for the routine work

$10/mo

$60 Sonnet allowance a month

**Requests / month**

≈2,050

**Per 5-hour window**

≈342req

**Each open-weight model**

$40/mo

**Model ID**

claude-sonnet-5-5

### Plus: Claude Opus 5.5

Best for Large refactors, long-running tasks

$30/mo

$200 Opus allowance a month

**Requests / month**

≈3,420

**Per 5-hour window**

≈570req

**Each open-weight model**

$125/mo

**Model ID**

claude-opus-5-5

### Pro: Claude Fable 5.2

Best for Several tasks at once and the hardest problems

$100/mo

$500 Fable allowance a month

**Requests / month**

≈5,090

**Per 5-hour window**

≈848req

**Each open-weight model**

$300/mo

**Model ID**

claude-fable-5-2

Estimates from CodingPass traffic: about 100K tokens per request at roughly 5% input, 1% output and 94% cache read. A single ZCode task usually makes several requests. Allowances are metered at official API prices.

## Three steps. About a minute.

ZCode keeps providers in its model settings. Switch one to API Key mode once and its models run through CodingPass.

1. ### Create a key
   Sign in with Google, GitHub or email and pick a plan. Then go to Dashboard → Keys → New key. Keys start with `cp-live-`.
2. ### Switch a provider to API Key
   Open the model picker, click Manage models, pick a provider and switch it to API Key mode in the top right. Claude models use the Anthropic URL, all others the OpenAI URL.
   `Manage models → API Key`
3. ### Pick the model
   Enter the model ID for your plan and choose it in the model picker of a new task. [Get your request ID](https://codingpass.ai/tools#check).
   `claude-sonnet-5-5`

acme-dashboard Example task ZCode

```
> Add a date range filter to the revenue chart.

● Goal 3 steps
● Edited src/charts/Revenue.tsx (+44 −7)
● Ran pnpm test · 19 passing
● Review 2 files changed
  The range defaults to the last 30 days and is kept in the URL.
```

Sonnet 5.5

$2.80 / $60.00 resets in 11d

## Get more out of every allowance.

One monthly allowance covers every model, with 5-hour and weekly caps. The right model for the task makes it go further.

### Use GLM on the OpenAI URL

ZCode is tuned for GLM. Add `glm-5.3-flash` under a provider that uses the OpenAI URL and use it for routine tasks: on Go it can use up to $40 a month from the shared allowance.

Go · up to, per model/mo ≈ req

Claude Sonnet 5.5 $60 ≈2,050

GLM-5.3-Flash $40 ≈10,100

Kimi K2.7 Code $40 ≈1,570

DeepSeek V4.1 Flash 1017 $40 ≈13,600

+ 4 more open-weight models, up to $40 each.

### Let it check the UI itself

For front-end tasks, give ZCode the page URL and say what done looks like. It opens the page in its built-in browser, takes a screenshot and fixes what it sees, so you don't spend a turn describing the UI.

```
Open http://localhost:5173/settings, switch to dark mode and take a screenshot. Fix any text that blends into the background.
```

## Questions about ZCode.

**Is this allowed? Could my account get banned?**

You use only your CodingPass key. You never log in to, share or relay anyone's account, so your own Claude or ChatGPT account isn't involved. Your requests follow each vendor's usage policy.

**Why two base URLs?**

ZCode talks to Claude models over the Anthropic API and to other models over the OpenAI API. CodingPass serves both with the same key: `https://codingpass.ai` for Anthropic, `https://codingpass.ai/v1` for OpenAI.

**Can I keep my GLM Coding Plan?**

Yes. Only the provider you switched to API Key mode uses CodingPass. Models bound to your Z.ai account keep working as before.

**What happens when I hit the 5-hour cap?**

Each 5-hour window allows 1/6 of the monthly allowance (on Go, $10 of Sonnet 5.5, about 342 requests). The cap counts all models together, so CodingPass then returns 429 with the reset time for every model. Wait for the reset, buy a reset card for the current window, or upgrade. [How caps and 429s work](https://codingpass.ai/usage-limits#response).

## Same key, every agent.
