API PRICES
Z.ai · GLM-4.5-Air
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 0.8 / output 2 CNY/million tokens智谱 ·
- Lowest inference provider (cash)
- Input 0.13 / output 0.85 USD/million tokensNovita AI ·
- Lowest relay (credit)
- 0.186 USD credit/million total tokens9527.codes "🇨🇳国产官方模型" ·
Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.
Z.ai · GLM-4.5-Air official price: input 0.8, output 2 CNY per million tokens (智谱, observed 2026-10-17). Cheapest inference provider: Novita AI, input 0.13, output 0.85 USD per million tokens. Cheapest relay: 9527.codes, group "🇨🇳Chinese official models [machine translation] (on site: 🇨🇳国产官方模型)" 0.186 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 41 sites have comparable prices; 69 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Official cash prices · Lowest 1.1 · median 2.1 · highest 2.9 · 3 quotes CNY / per million tokens
Inference provider cash prices · Lowest 0.31 · median 0.31 · highest 0.31 · 2 quotes USD / per million tokens
Inference provider cash prices · Lowest 2.25 · median 2.25 · highest 2.25 · 1 quotes CNY / per million tokens
Relay USD credit prices · Lowest 0.186 · median 0.186 · highest 0.186 · 1 quotes USD / per million tokens, site credit
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| 智谱 | 0.8 | 2 | 0.16 | — | CNY / 1M tokens | Official source | |
| 智谱 | 0.8 | 6 | 0.16 | — | CNY / 1M tokens | Official source | |
| 智谱 | 1.2 | 8 | 0.24 | — | CNY / 1M tokens | Official source |
Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.
Inference providers
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| Novita AI | 0.13 | 0.85 | 0.025 | — | USD / 1M tokens | Official source | ||
| OpenRouter · Aggregator | 0.13 | 0.85 | 0.025 | — | USD / 1M tokens | Official source | ||
| SiliconFlow | 1 | 6 | — | — | CNY / 1M tokens | Official source |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 0.186 · median 0.186 · highest 0.186 (1 quotes, USD credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | 9527.codesAsk or discussCollected: Collected this cycle View 1 plans 4 more sites of the same companyBasis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | 🇨🇳Chinese official models [machine translation]Group on site: 🇨🇳国产官方模型 Name on site: glm-4.5-air Chinese models-official full-strength-Volcano official agent channel [machine translation]Original: 国产模型-官方满血-火山官方代理渠道 Operator pending verification | 0.078 | 0.51 | 0.015 | 0.186Median price ÷ this price: 1× | Full prices and sources |
Related variants · 1 rows · not ranked
These are special editions of the model (thinking, max, search, batch, long context, free, etc.). They are priced differently from the base model, so they are listed separately and not ranked. Names that only add an effort level such as low, high or nothinking are compared with the base model.
- z-ai/glm-4.5-air-free (-free · free variant): 1 rows
- ai.38yun.cn · Official full-range stable channel [machine translation]Group on site: 官方全系稳定渠道 · z-ai/glm-4.5-air-free · Input 0 / Output 0 USD credits / 1M
How this ranking works
All per-token prices: 97,455 prices from 871 sites (about 765 companies). 89,631 are ranked, from 861 sites (about 755 companies); 7,824 more are listed separately and not ranked. Prices collected up to 2026-10-17.
This model has 147 recorded prices; 80 can be compared directly (78 ranked, 2 listed separately). Not comparable yet: price not parsed yet 34, ratio looks unset 13, scope of the official doc price not confirmed 8, tiered by rules (see Tiered prices) 7, display unit not confirmed 5
1 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.
Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.
“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for Z.ai · GLM-4.5-Air?
9527.codes, group "🇨🇳国产官方模型 (🇨🇳Chinese official models)", 0.186 USD credit per million total tokens, observed 2026-10-16. 41 sites have comparable prices.
What is the official price for Z.ai · GLM-4.5-Air?
Input 0.8, output 2 CNY per million tokens, checked 2026-10-17. Lowest inference provider: Novita AI, input 0.13, output 0.85 USD per million tokens.
How do I use Z.ai · GLM-4.5-Air in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest Z.ai · GLM-4.5-Air API to Claude Code for me". Install Skill →