> ZCode (GLM Coding Plan)
ZCode is Zhipu's official coding client for the GLM Coding Plan sold on bigmodel.cn, whose personal tiers are listed in CNY: ¥94.4/month (list ¥118) with 10,000 credits per week, ¥430.4/month (list ¥538) at six times the Lite allowance, and ¥862.4/month (list ¥1078) at fourteen times, each unlocking Claude Code, Codex, Cursor, OpenCode, Cline, Kilo Code and AutoClaw, with ZCode subscribers receiving 150% quota. The platform's API price list shows GLM-5.3 at 8 CNY per million input tokens and 28 CNY output, GLM-5.3-Flash at 0.8/2.8 CNY, GLM-TTS at 2 CNY per 10,000 characters, and Batch calls at half the standard price. New registered users receive 20 million tokens, and GLM-4.7-Flash (200K context) and GLM-4.6V-Flash are listed as free API models.
No API key stored by OmniRoute. The local ZCode app-server uses the existing builtin:zai-coding-plan login.
// pros
- Free API models are published with zero input, output and cache cost: GLM-4.7-Flash (200K context) and GLM-4.6V-Flash.
- New registered users receive 20 million tokens, with up to 200 million tokens available through the referral programme.
- Coding Plan entry price is low and explicit: ¥94.4/month discounted from ¥118, with 8折 quarterly and 7折 annual terms and 10,000 credits per week on the Lite tier.
- One subscription covers the supported tool chain — ZCode, Claude Code, Codex, Cursor, Cline, OpenCode, Kilo Code, AutoClaw — with documented Anthropic and OpenAI-compatible base URLs.
- ZCode subscribers get 150% quota, off-peak free tasks and data MCP access, and the team plan adds seat management with a stated default that enterprise data is not used for model training plus IP allowlisting.
// cons
- Coding Plan usage is credit/quota based (10,000 per week on Lite) and the plan is restricted to officially supported tools and product environments.
- Pricing and documentation are in Chinese CNY on bigmodel.cn, and the subscription and support flows are China-centric.
- Cache storage is only '限时免费' (free for a limited time) and promotional rates such as GLM-5.3-Flash at half price are time-boxed.
- Personal and team API keys are not interchangeable — team quota requires the team-plan key — which is an easy configuration error to make.
Use the GLM Coding Plan with ZCode if your engineers already live in Claude Code, Codex or Cursor and you would rather meter GLM usage as a flat weekly quota than track per-token spend; start at the ¥94.4/month Lite tier and upgrade only when the 10,000 weekly credits genuinely run out. For general API work, prototype on the free GLM-4.7-Flash and GLM-4.6V-Flash before paying 8 CNY per million input tokens for GLM-5.3.
written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026
Free tier present — value not quantified
This provider offers a free tier, but its terms don’t convert cleanly into a USD figure (e.g. request-count limits or capacity-dependent pools). We refuse to print a misleading zero here. See the note below and the official pricing page for the exact limits.
note: Allowance is 20,000,000 tokens for newly registered users ('新用户注册得 2000万 Tokens') plus up to 200 million tokens via referral on bigmodel.cn/pricing; no CNY or USD cash value is stated for the grant (checked 2026-09-16).
| Plan | Type | Monthly | Input /1M | Output /1M | Note |
|---|---|---|---|---|---|
| GLM Coding Lite | subscription | $12.60/mo | — | — | 10,000 credits/week (was $18/mo); rolling access to flagship models, 20+ agent tools. |
| GLM Coding Pro | subscription | $56.00/mo | — | — | 6x Lite usage (was $80/mo); priority model access, curated MCP tools, faster generation. |
| GLM Coding Max | subscription | $117.60/mo | — | — | 14x Lite usage (was $168/mo); first access to flagship models, dedicated peak-time resources. |
Pricing normalized from public sources — always verify with the provider.
// model prices
| Model | Input /1M | Output /1M | Context |
|---|---|---|---|
| Z.ai: GLM 4.7 Flash | $0.060 | $0.400 | 200k |
| Z.ai: GLM 5.3 Flash (batch) | $0.075 | $0.250 | 1.0M |
| Z.ai: GLM 4.5 Air | $0.130 | $0.850 | 131k |
| Z.ai: GLM 5.3 Flash | $0.150 | $0.500 | 1.3M |
| Z.ai: GLM 4.6V | $0.300 | $0.900 | 131k |
| Z.ai: GLM 4.7 | $0.400 | $1.75 | 205k |
| Z.ai: GLM 4.6 | $0.430 | $1.75 | 205k |
| GLM 5 | $0.600 | $1.92 | 205k |
| Z.ai: GLM 4.5V | $0.600 | $1.80 | 66k |
| GLM 4.5 | $0.600 | $2.20 | 131k |
| Z.ai: GLM 5.2 | $0.683 | $2.15 | 1.0M |
| Z.ai: GLM 5.3 (batch) | $0.700 | $2.20 | 1.0M |
| Z.ai: GLM 5.2 (batch) | $0.700 | $2.20 | 1.0M |
| Z.ai: GLM 5.1 | $0.966 | $3.04 | 205k |
| Z.ai: GLM 5V Turbo | $1.20 | $4.00 | 203k |
| GLM 5 Turbo | $1.20 | $4.00 | 203k |
| Z.ai: GLM 5.3 | $1.40 | $4.40 | 1.3M |
| glm-5.3 | — | — | 1.3M |
| glm-5.3-flash | — | — | 1.3M |
| GLM 5.2 | — | — | 1.0M |
$ Does ZCode (GLM Coding Plan) have a free tier?
Yes — ZCode (GLM Coding Plan) offers a free tier. Always confirm current limits on ZCode (GLM Coding Plan)'s official pricing page — free tiers change without notice.
$ How much does ZCode (GLM Coding Plan) cost per 1M tokens?
The cheapest model we track at ZCode (GLM Coding Plan) is $0.060 per 1M input tokens and $0.250 per 1M output tokens. This is normalized from ZCode (GLM Coding Plan)'s published pricing — verify with the provider before purchasing, since prices change frequently.
$ Is ZCode (GLM Coding Plan) safe to use?
Uprouter rates ZCode (GLM Coding Plan) as low risk. Low-to-moderate risk: plan prices, credit allowances, endpoint URLs and free models are all published on bigmodel.cn and in Zhipu's docs, so there is little hidden-fee exposure. The caveats are quota mechanics and currency — plan credits are weekly and tool-restricted, cache storage is only temporarily free, and billing is in CNY on a Chinese platform, so invoicing, tax and any data-residency requirements need checking. The stronger enterprise assurances (no training on enterprise data by default, IP allowlisting) are stated for the team plan, not the personal tiers. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.
Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.
No published reviews yet — be the first.
// more_informationprice history · live status · risk & confidence · code snippets
price_history
No recorded changes yet.
live_status
current: unknownNo probes recorded yet.
Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.
risk_&_confidence
Low-to-moderate risk: plan prices, credit allowances, endpoint URLs and free models are all published on bigmodel.cn and in Zhipu's docs, so there is little hidden-fee exposure. The caveats are quota mechanics and currency — plan credits are weekly and tool-restricted, cache storage is only temporarily free, and billing is in CNY on a Chinese platform, so invoicing, tax and any data-residency requirements need checking. The stronger enterprise assurances (no training on enterprise data by default, IP allowlisting) are stated for the team plan, not the personal tiers.
Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.
code_snippets
# ZCode (GLM Coding Plan)'s own API — get a key from their dashboard
curl https://zcode.z.ai/chat/completions \
-H "Authorization: Bearer THEIR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5-3",
"messages": [{ "role": "user", "content": "Hello" }]
}'Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.
Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.