SHELFCRITTER AI Digest

TOOL

ZCode

tooltopic-notezhipuchinacoding-agent

Overview

ZCode is Zhipu AI‘s July 2026 coding-agent product built on GLM 5.2 — a first-class Chinese competitor to Claude Code and OpenAI Codex. Launched with a 1M-token context window, aggressive trial economics (5M free tokens/day for five days), paid plans starting $18/month, and API pricing at ~1/6th of GPT-5.5, ZCode extends Zhipu’s earlier zcode.z.ai harness surface into a first-party coding-agent product with pricing as the load-bearing news.

Timeline

  • 2026-07-08-AI-Digest — Zhipu AI shipped ZCode, positioning explicitly against Claude Code and OpenAI Codex — 1M-token context, five-day new-user trial of 5M free tokens per day (3M GLM 5.2 + 2M GLM-5-turbo), paid plans starting $18/month, and API pricing at $1.40 / $4.40 per M in/out (~1/6th of GPT-5.5). The Decoder cites a Snowflake CEO write-up of a 103-task dbt-bench comparison in which GLM 5.2 and Claude Opus 4.7 land 66% vs 67% at Pass@3 — but with a wider first-attempt gap (47.6% vs 53.7%) and roughly 2× the token usage on the GLM 5.2 side. Narrow read: on one SQL-coding benchmark at three attempts near-parity, but the Pass@1 gap and 2× token cost tell a different story about single-shot reliability and inference economics. Structural read the digest carries: the pricing is the news, not the benchmark — a gated 5-day trial at 5M tokens/day plus $18/month paid plans is the most aggressive coding-agent economics any Chinese lab has taken to market against Claude Code, and it pairs with today’s Tencent Hy3 open-weights release as two independent pressure points on the coding-agent cost stack in one week.

Key Developments

  1. Chinese Claude Code / Codex Competitor with 1M Context (July 8, 2026): First full-stack Chinese coding agent positioned explicitly against Claude Code and OpenAI Codex — 1M-token context, five-day trial at 5M tokens/day, $18/mo paid plans, ~1/6th GPT-5.5 API pricing.

  2. Pricing as the Story, Not the Benchmark: The GLM 5.2 / Claude Opus 4.7 66%/67% Pass@3 dbt-bench near-tie is a single-benchmark result at three attempts with a 2× token cost — not a general parity claim. The load-bearing news is the aggressive trial + paid economics, not model capability.

  3. Zhipu Full-Stack Product Play: ZCode extends Zhipu’s earlier zcode.z.ai harness (previewed on 2026-07-02-AI-Digest via GLM 5.2‘s coding-agent harness announcement) into a first-party product surface, consolidating Zhipu’s open-weights model line under a first-party coding-agent rather than leaving distribution to third-party wrappers.

See also: Zhipu AI, GLM 5.2, Claude Code, MOC - Open Source Models, MOC - Developer Tools.