Zhipu Token API Pricing, Top-up, Deals & Updates | Article

Zhipu Token API pricing. GLM-5.3, GLM-5.2 and 46 more models. OpenAI-compatible API, Anthropic-compatible API, Context Cache and 3 more tools integrations. Includes cache tiers and rate limits. API key setup, usage quotas, and official entry—is it worth it?

41
Platforms
395+
Models
140+
IDE Tools
48
Zhipu Token API models
¥0.8 / ¥2
Zhipu Token API entry price
View
Vendor details

GLM API Latest Updates

Zhipu ZCode Hits 1M Users, Launches Goal, Subagents, and More — Coding Agent Goes Autonomous

Published Updated
ProductZhipuZCodeCoding AgentProduct UpdateGLM-5.2Claude Code
Summary

Zhipu ZCode shipped a major upgrade on August 11 with four new features — Goal (target-driven execution), Subagents (parallel task splitting), Remote Control, and Idle Tasks. The Coding Agent moves from chat-based assistance to autonomous complex task delivery. User count breaks 1 million; GLM Coding Plan weekly quotas reset for all. Paired with GLM-5.2, task pass rate beats Claude Code by 2.39%. Cache optimization boosts effective quota ~30%, plus a 1.5× quota campaign runs through August 31.

Zhipu ZCode just dropped a major upgrade today: four new features — Goal, Subagents, Remote Control, and Idle Tasks — and the user count hit 1 million. The real story isn't the feature list. It's the shift in positioning: ZCode is no longer "an assistant that helps you write code." It's now "an Agent that ships complex projects on its own."

On August 11, Zhipu announced the ZCode overhaul (source). Alongside the upgrade, all GLM Coding Plan weekly quotas were fully reset at 13:00 Beijing time.

Four Features: The Agent Finally Runs the Whole Pipeline

This upgrade adds a full "goal management + autonomous execution" layer to the Coding Agent. Before, ZCode worked like a conversational coding assistant — you ask, it answers, you iterate. Now you give it a verifiable goal and it plans, executes, traces, and verifies — end to end.

Goal: Target-Driven Autonomous Loop

This is the centerpiece. Set a verifiable target — "refactor the user module and pass all regression tests" — and ZCode handles the rest:

  1. Auto-decompose the task
  2. Modify code
  3. Run commands, execute tests
  4. Evaluate completion based on file changes, command output, and test results
  5. If the target isn't met, loop again until it is

The Goal dashboard shows per-round progress, duration, and results. You don't need to babysit it.

Subagents: Decompose and Run in Parallel

Large tasks get automatically split into subtasks, assigned to different modules running in parallel. Cross-file, cross-module coordinated changes that used to require manual context switching are now handled by Subagents autonomously.

Remote Control: Progress Anywhere

Once a task is running, switch to other windows and do your own thing. Remote Control lets you check progress from anywhere. Built for long-running tasks that take hours.

Idle Tasks: Smart Scheduling

Non-urgent tasks don't compete with real-time calls during peak hours. They automatically execute during low-load periods — saves quota and avoids contention.

Performance: GLM-5.2 + ZCode vs. + Claude Code

Zhipu's internal Z.ai Code Bench shows GLM-5.2 + ZCode outperforming GLM-5.2 + Claude Code by 2.39% in overall task pass rate. (source)

Metric GLM-5.2 + ZCode GLM-5.2 + Claude Code
Overall task pass rate +2.39% Baseline
Complex cross-file tasks Gap widens
Cache optimization GLM Coding Plan quota +~30%
Campaign boost 1.5× through Aug 31

2.39% may sound modest, but this is an overall pass rate including both simple and complex tasks. The advantage concentrates on cross-file, multi-stage tasks requiring final verification — there, the gap is substantially wider.

Two reasons ZCode pulls ahead: cache hit rate optimization boosted Coding Plan effective quota by ~30% (more rounds for the same budget), and the Goal + Subagents decomposition algorithm was specifically tuned for the GLM family.

1 Million Users + Full Quota Reset

ZCode officially crossed 1 million users (source). As a milestone celebration, all GLM Coding Plan weekly quotas were fully reset on August 11.

Combined with the 1.5× quota campaign running through August 31, actual usable capacity nearly doubles:

Tier Normal Weekly Quota Current (1.5× + cache boost)
Lite ~400 prompts/week ~780 prompts/week
Pro ~2000 prompts/week ~3900 prompts/week
Max ~8000 prompts/week ~15600 prompts/week

GLM-5.2 / GLM-5-Turbo peak multiplier stays at 3×, but off-peak usage during the 1.5× campaign only burns at 1× instead of 2×.

Zhipu's Coding Ecosystem Comes Together

Zoom out, and this upgrade completes the third pillar of Zhipu's "base model + Coding Harness + subscription service" architecture. GLM-5.2 provides the model capability. The Coding Plan bridges compute to developers. ZCode closes the loop on Agent execution in real engineering environments.

Claude Code is more general and supports more models, but it's Anthropic's toolchain — it will never be deeply optimized for GLM. ZCode's tight GLM-family coupling is its moat.

Caveats

  1. ZCode currently only supports GLM-series models — no mixing with DeepSeek, Kimi, or other third-party APIs. For multi-model setups, Claude Code or Cursor remain more flexible.
  2. The 1.5× quota campaign and full reset are time-limited — they end August 31.
  3. Goal is fundamentally an autonomous Agent loop. Complex task success depends on model capability and task decomposition quality — real-world experience will vary by task type.
  4. If the Coding Plan cache storage policy changes in the future, the sustainability of the quota boost would be directly affected.

Sources and verification

Last verified

Zhipu Token API FAQ

How do ZCode's new Goal, Subagents, Remote Control, and Idle Tasks features actually work, and what's fundamentally different from before?

The core shift is ZCode moving from a chat-based assistant to an Agent that autonomously completes complex tasks. Goal lets you set a verifiable target — the Agent then breaks it down, modifies code, runs tests, evaluates completion, and loops until done. Subagents split large tasks into parallel subtasks. Remote Control gives you live progress monitoring. Idle Tasks run non-urgent work during low-load periods. Before, ZCode was closer to advanced autocomplete; now it walks the full 'requirements → coding → testing → verification' pipeline on its own.

Does GLM-5.2 paired with ZCode actually outperform the same model paired with Claude Code, and what does Z.ai Code Bench show?

Zhipu's internal Z.ai Code Bench shows GLM-5.2 + ZCode achieving a 2.39% higher overall task pass rate than GLM-5.2 + Claude Code. The gap widens significantly on complex cross-file, multi-stage tasks requiring final verification — exactly where general-purpose frameworks like Claude Code struggle. This isn't surprising: ZCode is a domestic Coding Harness purpose-built for the GLM family, so the integration tightness is inherently higher.

What happens to GLM Coding Plan quotas after ZCode hits 1 million users, and how long does the 1.5× campaign run?

On August 11, all GLM Coding Plan users got their weekly limits fully reset as a milestone celebration. ZCode also boosted effective quotas by ~30% through cache hit rate optimization. Combined with the 1.5× quota campaign running through August 31, actual usable capacity nearly doubles. For GLM-5.2/GLM-5-Turbo users, off-peak usage during the campaign only burns at 1× the quota multiplier instead of the normal 2×.

How does Zhipu ZCode compare to Claude Code or Cursor for coding Agent work — what are the trade-offs?

ZCode's strength is deep GLM model adaptation — the 2.39% uplift in Z.ai Code Bench comes from cache optimization and the task-splitting algorithm, both tuned specifically for GLM. If GLM Coding Plan is your primary setup, ZCode is the optimal choice. If you need to mix models (DeepSeek, Kimi, etc.), Claude Code or Cursor offer broader model support. ZCode currently only supports GLM-series models with no third-party API mixing.
AI Token Plan

Global AI Token Comparison

AI Token Plan is not just a collection of vendor links. It places 41+ domestic and international AI platforms into one comparison framework, covering 395+ model entries plus common plan types such as Token Plans, Coding Plans, IDE Tools and LLM APIs.

When you need to compare AI subscription pricing, coding plan quota, API usage cost or official deal entry points, AI Token Plan brings official prices, plan tiers, usage rules, model capabilities and tool integrations into one place, reducing the need to check multiple vendor sites manually.

Data is continuously organized as vendor pricing pages, plan pages and product documentation change, making the homepage a pricing comparison entry point while detail pages explain whether each vendor plan fits individual developers, team purchasing or long-term API usage.

Prices come from each platform's official site and may change at any time; the official price prevails.

© 2026 AI Token Plan · All rights reserved · First published June 18, 2026 · 64 days running · Sitemap