# Editorial re-verification: GLM Coding (China)

> Source: <https://www.uprouter.online/s/glm-cn>
> Published: 2026-09-16 21:08:22+00:00

# > GLM Coding (China)

[open.bigmodel.cn](https://open.bigmodel.cn/pricing)

Zhipu AI's GLM platform (bigmodel.cn, also served at open.bigmodel.cn) sells model access per token in CNY and bundles agentic coding into a separate GLM Coding Plan. The official pricing page lists GLM-5.3 at 8 yuan per million input tokens, 2 yuan per million cached tokens and 28 yuan per million output tokens with a 1M-token context, and GLM-5.3-Flash at 0.8 / 0.23 / 2.8 yuan. New accounts receive 20 million free tokens on registration, and the text model GLM-4.7-Flash (200K context) and vision model GLM-4.6V-Flash are listed as free for input, output and cache. The GLM Coding Plan shows 118 yuan/month (Lite), 538 yuan/month (Pro) and 1078 yuan/month (Max), with discounted continuous-subscription prices of 94.4 / 430.4 / 862.4 yuan and quarterly billing at 8-fold and annual at 7-fold discounts.

### // pros

- Two API models are priced at zero: GLM-4.7-Flash (200K context) and GLM-4.6V-Flash are stated as free for input, output and cache on the official pricing page.
- New-user grant of 20 million tokens: the pricing page states new registrations receive 20,000,000 tokens, with up to 200 million tokens reachable through the referral programme.
- GLM Coding Plan Lite is 118 yuan/month list (94.4 yuan on the discounted continuous options) and includes 10,000 credits per week plus support for 20+ coding tools including Claude Code, Codex, Cursor and OpenCode.
- Tier scaling is explicit: Pro is 6x the Lite usage allowance and Max 14x, with quarterly billing at an 8-fold discount and annual at 7-fold.
- Flagship GLM-5.3 offers a 1M-token context at 8 yuan per million input and 28 yuan per million output tokens, and the Batch API is billed at 50% of standard rates.

### // cons

- The 20 million tokens are a one-time registration bonus, not a recurring free allowance; no perpetual free chat tier is documented.
- Coding-plan quota is expressed as 10,000 credits per week, so sustained agent use is capped and the allowance resets weekly.
- All prices are quoted in CNY on a Chinese-language console; no USD list price appears on the pages fetched.
- Cache storage is marked free for a limited time only, signalling that the zero-cost cache component is temporary.

Start with GLM-4.7-Flash and GLM-4.6V-Flash for zero-cost prototyping, then add GLM Coding Plan Lite (94.4 yuan/month on continuous billing) if you want Claude Code-style agent work, moving to Pro or Max only when the weekly credit allowance becomes the bottleneck.

imported analysis — independent third party, not Uprouter editorial · verify before relying on it

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: Free grant is 20,000,000 GLM tokens for new registrations (tokens, not currency), stated on bigmodel.cn/pricing and bigmodel.cn/claude-code; GLM-4.7-Flash and GLM-4.6V-Flash are additionally free per token.

| Plan | Type | Monthly | Input /1M | Output /1M | Note | 
|---|---|---|---|---|---|
| Pay-as-you-go | payg | — | Free | Free | Cheapest tracked model rate (OpenRouter-normalized). | 
| GLM-5.3 | payg | — | $1.13 | $3.94 | Converted from 8 RMB / 28 RMB per 1M (1 USD = 7.1 CNY). | 
| GLM-4.7-Flash | free | — | — | — | Permanently free for both input and output. | 

[official pricing page](https://bigmodel.cn/pricing)

Pricing normalized from public sources — always verify with the provider.

### // model prices

| Model | Input /1M | Output /1M | Context | 
|---|---|---|---|
| [glm-5.3-flash](https://www.uprouter.online/models/glm-5-3-flash) | Free | Free | 1.3M | 
| [glm-5.3](https://www.uprouter.online/models/glm-5-3) | $0.0000 | $0.0000 | 1.3M | 
| [GLM 5 Turbo](https://www.uprouter.online/models/z-ai/glm-5-turbo) | $0.0000 | $0.0000 | 203k | 

## $ Does GLM Coding (China) have a free tier?

Yes — GLM Coding (China) offers a free tier. Always confirm current limits on GLM Coding (China)'s official pricing page — free tiers change without notice.

## $ How much does GLM Coding (China) cost per 1M tokens?

The cheapest model we track at GLM Coding (China) is Free per 1M input tokens and Free per 1M output tokens. This is normalized from GLM Coding (China)'s published pricing — verify with the provider before purchasing, since prices change frequently.

## $ Is GLM Coding (China) safe to use?

Uprouter rates GLM Coding (China) as low risk. Medium risk. The pricing pages carry an explicit plan-benefit change notice, several discounts are marked limited-time, and the platform operates in CNY with real-name registration required for the referral token bonus. On the positive side, the coding-plan documentation states that enterprise data is not used for model training by default and that IP whitelisting is supported, which lowers data-handling risk for team use. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.

## $ Can I use GLM Coding (China) through Uprouter Connect?

Yes — GLM Coding (China) is Connect-compatible. Add your GLM Coding (China) API key in Uprouter Connect (encrypted at rest) and route requests to it through one OpenAI- and Claude-compatible API, optionally behind failover aliases. Uprouter meters the traffic in compute at the provider's listed rate.

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: unknown
No 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

Medium risk. The pricing pages carry an explicit plan-benefit change notice, several discounts are marked limited-time, and the platform operates in CNY with real-name registration required for the referral token bonus. On the positive side, the coding-plan documentation states that enterprise data is not used for model training by default and that IP whitelisting is supported, which lowers data-handling risk for team use.

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

```
curl https://www.uprouter.online/api/connect/v1/chat/completions \  -H "Authorization: Bearer upr_live_YOUR_KEY" \  -H "Content-Type: application/json" \  -d '{
    "model": "glm-5-3",
    "messages": [{ "role": "user", "content": "Hello via GLM Coding (China)" }]
  }'
```

Metered in Uprouter compute — the usage log shows which upstream served each request and its exact cost.

[NLP Cloudfree $15.00 est.pricing n/aconnectLow risk](https://www.uprouter.online/s/nlpcloud-com)

[Nomicfree $0.10 est.pricing n/aconnectLow risk](https://www.uprouter.online/s/nomic-ai)

[Lightning AIfree $15.00 est.pricing n/aconnectLow risk](https://www.uprouter.online/s/lightning-ai)

[AI21 Labsfree $10.00pricing n/aconnectLow risk](https://www.uprouter.online/s/api-ai21-com)

Ranked by neutral similarity signals only — live status, Connect compatibility, free-tier shape and free-credit proximity. Commercial relationships never influence this list.