| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| hvoy | Token | ¥4.01 | ¥14.02 | ¥0.9855 | ¥0.9855 |
Zhipu AI
GLM 5.3
Next-generation GLM for reasoning, tools, and long-horizon coding
GLM 5.3 is Zhipu's next-generation flagship for reasoning, tool use, and long-horizon coding, with open weights and about 1M context. Best for engineering work, agent orchestration, and production jobs that need stable long-context execution; verify exact capabilities and endpoints with the official channel.
1M-token context1M
Released2026-08
Relays63 sites
ReasoningToolsOpen weights1M context
Zhipu AI Official Pricing
CNYUpdated: 2026-08-19T12:04:48.443+08:00Source
observed_hvoyweb · Input
~¥8/ 1M tokens
Observed in the hvoyweb active model catalog on 2026-08-18; verify the Zhipu official pricing page before publishing.
observed_hvoyweb · Output
~¥28/ 1M tokens
Observed in the hvoyweb active model catalog on 2026-08-18; verify the Zhipu official pricing page before publishing.
observed_hvoyweb · Cache read
~¥2/ 1M tokens
Observed in the hvoyweb active model catalog on 2026-08-18; verify the Zhipu official pricing page before publishing.
Observed in the hvoyweb active model catalog on 2026-08-18; verify the Zhipu official pricing page before publishing.
Relay Comparison
Compare token, per-request, or per-second pricing by relay channel.
Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit
Price range ¥8 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| default | Token | ¥8 | ¥28 | ¥2 | - |
GLM-Deploy-SR
BillingToken
Input¥5
Output¥15.73
Cache hit¥0.9295
Cache write¥5
max
BillingToken
Input¥5
Output¥15.73
Cache hit¥0.9295
Cache write¥5
GLM-Deploy-S
BillingToken
Input¥5.46
Output¥17.16
Cache hit¥1.01
Cache write¥5.46
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| GLM-Deploy-SR | Token | ¥5 | ¥15.73 | ¥0.9295 | ¥5 |
| max | Token | ¥5 | ¥15.73 | ¥0.9295 | ¥5 |
| GLM-Deploy-S | Token | ¥5.46 | ¥17.16 | ¥1.01 | ¥5.46 |
Price range ¥3.85 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| glm-stable | Token | ¥3.85 | ¥13.46 | ¥0.9614 | - |
Price range ¥1.2 / 1M tokens
GLM
BillingToken
Input¥1.2
Output¥4.2
Cache hit¥0.3
Cache write-
国模统一分组
BillingToken
Input¥1.2
Output¥4.2
Cache hit¥0.3
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| GLM | Token | ¥1.2 | ¥4.2 | ¥0.3 | - |
| 国模统一分组 | Token | ¥1.2 | ¥4.2 | ¥0.3 | - |
Price range ¥4.8 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国产官方模型 | Token | ¥4.8 | ¥16.8 | ¥1.2 | - |
Price range ¥1.88 / 1M tokens
国模2折福利
BillingToken
Input¥1.88
Output¥5.89
Cache hit¥0.3483
Cache write¥0
国模福利-chat端点
BillingToken
Input¥1.88
Output¥5.89
Cache hit¥0.3483
Cache write¥0
国模福利-messages端点
BillingToken
Input¥1.88
Output¥5.89
Cache hit¥0.3483
Cache write¥0
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| 国模2折福利 | Token | ¥1.88 | ¥5.89 | ¥0.3483 | ¥0 |
| 国模福利-chat端点 | Token | ¥1.88 | ¥5.89 | ¥0.3483 | ¥0 |
| 国模福利-messages端点 | Token | ¥1.88 | ¥5.89 | ¥0.3483 | ¥0 |
Price range ¥4 - ¥5.6 / 1M tokens
GLM智谱开源
BillingToken
Input¥4
Output¥14
Cache hit¥1
Cache write-
GLM智谱官转
BillingToken
Input¥5.6
Output¥19.6
Cache hit¥1.4
Cache write-
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| GLM智谱开源 | Token | ¥4 | ¥14 | ¥1 | - |
| GLM智谱官转 | Token | ¥5.6 | ¥19.6 | ¥1.4 | - |
Price range ¥5 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| glm | Token | ¥5 | ¥17.5 | ¥1.25 | - |
Price range ¥1.44 / 1M tokens
| Channel | Billing | Input | Output | Cache hit | Cache write |
|---|---|---|---|---|---|
| GLM | Token | ¥1.44 | ¥5.04 | ¥0.36 | - |
How should GLM 5.3 relay pricing be compared?
This GLM 5.3 pricing page compares official pricing with public prices from 63 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: 09/20/2026, 15:34.
- Data sources
- Public price catalogs, official pricing records, and monitoring results.
- Metric definitions
- Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
- Risk note
- Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.