grandet.
中文Explore Grandet
Menu

API PRICES

Z.ai · GLM-4.6

Provider prices, cheapest first

Browse all models

Z.ai · GLM-4.6 official price: not yet recorded. Cheapest inference provider: OpenRouter, input 0.5, output 2 USD per million tokens. Relays have only older quotes; the lowest is api.xhuoai.com, group "deepseek" 2.1 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-10). 50 sites have comparable prices; 91 sites list this model.Relay blended price uses 75% input and 25% output.

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

ProviderInputOutputCache readCache writeUnitObservedConditions and sourcevs official
OpenRouter · Aggregator0.520.1—USD / 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.

Filtering by provider: api.xhuoai.com

Searching…

Browse all providers
Clear filters

Blended price = input × 75% + output × 25%, without cache.

sites have comparable prices5091 sites list this model; approximately 1 operators
Older lowest input price (reference)1.2USD credits / 1M
Median of each provider’s lowest price1.2USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Older price
01api.xhuoai.comAsk or discussCollected:
View 3 plans		deepseek
Name on site: glm-4.6
Deepseek stable channel, Chinese model, strong coding ability, very high value for money, 60% of list price, rate multiplier 0.6 [machine translation]Original: Deepseek稳定渠道，国产模型，代码能力强，性价比极高，6折，倍率0.6
1.24.8—2.1Full prices and sources
02api.xhuoai.comAsk or discussCollected:
View 3 plans		default
Name on site: glm-4.6
Default group, supports all common models, OpenAI special-price channel (AZ Microsoft channel) Claude Code, Gemini stable channel (GCP/Velax), top value-for-money choice, 20% of list price, rate multiplier 1.0 [machine translation]Original: 默认分组，支持所有常用模型,OpenAI特价渠道（AZ微软渠道）Claude Code,Gemini稳定渠道（GCP/Velax），性价比首选，2折，倍率1.0
28—3.5Full prices and sources
03api.xhuoai.comAsk or discussCollected:
View 3 plans		Enterprise channel [machine translation]Group on site: 企业渠道
Name on site: glm-4.6
OpenAI/Claude enterprise-grade channel, top choice for top speed and stability, ultra-high concurrency, features identical to official, 5.6/10 of list price, rate multiplier 4.0 [machine translation]Original: OpenAI/Claude企业级渠道，追求极速稳定首选，超高并发，功能与官方完全一致，5.6折，倍率4.0
832—14Full prices and sources
Special groups · 2 rows · not ranked

These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.

  • test or debug group: 2 rows
  • hk.apitoken.ai · sandbox-China · glm-4.6 · Input 0.286 / Output 1.142000002 USD credits / 1M
  • hk.apitoken.ai · sandbox · glm-4.6 · Input 0.286 / Output 1.142000002 USD credits / 1M
View all 2 rows →
How this ranking works

All per-token prices: 96,427 prices from 839 sites (about 733 companies). 88,950 are ranked, from 826 sites (about 720 companies); 7,477 more are listed separately and not ranked. Prices collected up to 2026-10-10.

This model has 213 recorded prices; 106 can be compared directly (102 ranked, 4 listed separately). Not comparable yet: new price under review; showing the previous one 36, price not parsed yet 34, display unit not confirmed 11, scope of the official doc price not confirmed 8, ratio looks unset 7, tiered by rules (see Tiered prices) 6, billed per request or another unit 5

0 recent · 3 stale (older than 7 days, or not updated by this refresh) · 0 unverified timestamps. Only older prices are available, so the statistics are for reference only. 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.

Full methodology →

Switch model