Tabbit
ResourcesBlogModels
Tabbit LogoTabbit

Tabbit — The AI Browser that Works for You

Topics

  • Best Browsers 2026: Rankings and Top Lists
  • AI Browser Guides and Resources
  • Browser Comparisons: Head-to-Head Guides
  • Browser Reviews and Explainers
  • Browser Alternatives
  • Browser Directory: Guides by Browser
  • Agentic Browser Resources
  • Browser Downloads and Install Guides
  • Browser Productivity Resources
  • SillyTavern Model Guides and Presets

Popular Guides

  • Best Browsers 2026: Top 10 Ranked & Compared
  • Best Free AI Browsers 2026: Plans & Prices Compared
  • Rabbit Browser: What It Is & Why Tabbit Is Better
  • Firefox vs Chrome 2026: Privacy, RAM & Speed Compared
  • Best Lightweight Browsers 2026: 7 Tested for RAM & Speed
  • AI Browser List 2026: 10 Browsers Compared
  • Neobrowser: Norton Neo, Download & Alternatives
  • Edge vs Chrome 2026: Speed, RAM & Battery Tested
  • Best Internet Browser for Android 2026
  • Best AI Browser 2026: Top 9 Tested & Ranked

Events

  • Tabbit Skill Competition
  • KPOP SBTI Fandom Personality Test
  • Tabbit Campus Creator Program
  • fifi's Picks: AI Skills for Research Papers
  • User Survey

About

  • Tabbit Blog
  • Press & Media
English
简体中文English
Showcases & prompts

GLM-5.3 · Configuration

Migrate GLM-5.3 thinking parameters

Migrate a legacy disabled-thinking request to GLM-5.3 enabled thinking with an explicit low/high/max tier.

Source reviewed; not testedZ.ai API documentation and an OpenAI-compatible client

Prerequisites and inputs

  • legacy request body
  • target model ID
  • regression case

Complete templates

Editorial adaptation: auditable workflow

Tabbit editorial adaptation; not the original source prompt
Run one reversible GLM-5.3 task with these inputs:

- legacy request body: {{LEGACY_REQUEST_BODY}}
- target model ID: {{TARGET_MODEL_ID}}
- regression case: {{REGRESSION_CASE}}

State the plan, environment, and acceptance criteria; get human approval, then separate source facts, model output, and items still to verify.

Replace before running: legacy request body, target model ID, regression case

Steps

  1. Locate the legacy thinking.type: "disabled" and model ID.

  2. Switch to glm-5.3, set thinking.type: "enabled", and begin regression with reasoning_effort: "low".

  3. Run minimal cases for tools, streaming, and structured output, keeping the old config for rollback.

Read the source research notes

Core content summary

The official Z.ai documentation for the GLM-5.3 text model covers its capabilities, feature changes, parameter descriptions, and integration details—the first-hand authoritative reference for prompt design and API calls.

Overview

  • GLM-5.3 is Z.ai's latest flagship model, with major advances across complex software engineering and Agent tasks. It uses the same base model as GLM-5.2; all improvements come from post-training.

  • Stronger coding: Z.ai's internal Z.ai Code Bench score is up 50% versus GLM-5.2; Terminal Bench 3.0 and Agents' Last Exam (CLI) are open-source SOTA.

  • Emergent cybersecurity capabilities: CyberGym is currently best in vulnerability discovery; the deeper the exploitation chain, the more significant the gains (the vulnerability-exploitation benchmark score is more than twice that of 5.2).

Key feature changes

  • Text modality only; a 1M-token context window and a maximum output of 128K tokens.

  • Thinking is always enabled, with three reasoning-intensity levels: low, high, and max; disabling thinking is no longer supported.

ParameterValuesDefaultDescription
thinking.typeenabledenabledOnly enabled thinking is supported; disabling thinking is not supported
reasoning_effortlow, high, maxmaxlow—lightweight reasoning; high—enhanced reasoning; max—deep reasoning
  • Migration note: If an application currently uses thinking.type: "disabled", change it to enabled and set reasoning_effort to low before updating the model ID to glm-5.3. Otherwise, the request will fail.

  • For complex tasks such as coding, max is recommended. Example:

{
  "model": "glm-5.3",
  "thinking": { "type": "enabled" },
  "reasoning_effort": "max"
}

How to use

  • GLM Coding Plan: Fully available, with GLM-5.3 supported in commonly used coding agents. The new version uses a credit-based quota system; calls during off-peak periods (including all day on weekends) consume only 50% of the standard credits.

  • Model API: Coming soon; supported protocols and integration endpoints:

    • OpenAI Chat Completion protocol: https://open.bigmodel.cn/api/paas/v4

    • OpenAI Response protocol: https://open.bigmodel.cn/api/v1

    • Anthropic Message protocol: https://open.bigmodel.cn/api/anthropic

  • Supported capabilities: thinking mode, streaming output, Function Calling (tool calls), context caching, and structured output (JSON and more).

Official capability details (for prompt design reference)

  • The training environment shifted from traditional programming problems to "complete professional work units": some tasks take a senior engineer several days to complete (for example, an ML infrastructure task: identify a bottleneck in the training stack → implement an optimization → run experiments → deliver measurable end-to-end acceleration).

  • Validators are generated without reference solutions and are used for training only after checks with an oracle, no-op, or unresolved state; the RL strategy of SAO with compaction continues.

  • Z.ai Code Bench: 34.5% at the Max tier with approximately 75,000 tokens (5.2 was 23.4% at approximately 96,000); 31.4% at the High tier with approximately 50,000 tokens, exceeding Opus 4.8 (29.5% at approximately 120,000); Fable 5 still leads at 39.5% at the Max tier.

  • Cybersecurity: CyberGym 84.5% (best, ahead of Mythos 5 at 83.8% and GPT-5.6 Sol at 83.6%); ExploitBench 54.4% (5.2 was 24.4%, more than doubled); ExploitGym 2h/6h = 105/130; 2,436 vulnerabilities across 269 real-world codebases (1,097 medium- or high-severity), with the oldest vulnerability remaining latent for approximately 40 years.

Prompt design takeaways (based on official guidance)

  1. Thinking cannot be disabled: There is no need to tell the prompt to "stop thinking"; use reasoning_effort to select a tier instead—low for simple tasks to save tokens, and max for complex coding or Agent tasks.

  2. Treat the model as a "structured engineering model," not a conversational chatbot: Describe tasks, data, and constraints separately.

  3. Make good use of tool calls and structured output: The official service supports Function Calling, JSON structured output, and context caching; prompts can declare schemas and tools.

  4. When migrating an existing application, change thinking.type and reasoning_effort first, then switch the model ID.

Source and dates

Z.ai Open Documentation (docs.bigmodel.cn, official) · Source date: 2026-08 · Edited: 2026-09-20

Read the original source
Variable checklist

Still to replace: 3

legacy request bodytarget model IDregression case

Related showcases & prompts

Configure three reasoning tiers across API protocolsChoose reasoning effort by task difficultyBuild staged coding tasks with explicit contextPlan before editing in ZCode

Related reviews

X (Twitter) @Rafa_Schwinger: Metal Kernel Review Task—GLM 5.3 xhigh 88/100 vs. Grok 4.6 86/100Z.ai Official Technical Blog: Frontier Coding and Emergent Cybersecurity Capabilities (Z.ai)GLM-5.3 Review: Advanced Cybersecurity Capabilities and Coding Gains (VentureBeat)GLM-5.3 Independent Benchmark: 91.25% on KingBench 3, Taking the Top Spot (MindStudio)

Read the full analysis

Overview · English

GLM-5.3 Explained: What Changed from GLM-5.2

GLM-5.3 keeps the GLM-5.2 base but adds post-training for longer coding and agent tasks. Compare the changes, access paths, costs, and open risks.

GLM-5.3

Use GLM-5.3 in Tabbit

Run this guide in the environment listed above. Downloading does not transfer the template or establish model availability for your account.