API pricing

# Z.ai (Zhipu) API pricing

> Z.ai (Zhipu) API prices run from $0.06 per million input tokens (GLM-4.7-Flash) to $2.80 (GLM 5.3 Prime). Its highest-ranked model, GLM-5.3, costs $1.40 input and $4.40 output per million tokens.
- Canonical page: https://noometry.com/llm-pricing/zai
- Last updated: 2026-10-10
- Title: Z.ai (Zhipu) API Pricing (October 2026): Every Model per 1M Tokens

Z.ai (Zhipu) API prices run from $0.06 per million input tokens (GLM-4.7-Flash) to $2.80 (GLM 5.3 Prime). Its highest-ranked model, GLM-5.3, costs $1.40 input and $4.40 output per million tokens.

Last verified October 10, 2026

Official price list: [docs.z.ai](https://docs.z.ai/guides/overview/pricing)

API prices per million tokens
|  |  |  | Cached input |  |  |  |
| --- | --- | --- | --- | --- | --- | --- |
| [GLM-4.7-Flash](https://noometry.com/models/glm-4-7-flash) (open weights) | $0.06 | $0.40 | $0.01 | **$0.15** | 200K | 38.8 |
| [GLM-4.7-FlashX](https://noometry.com/models/glm-4-7-flashx) (open weights) | $0.07 | $0.40 | $0.01 | **$0.15** | 200K | — |
| [GLM-5.3-Flash](https://noometry.com/models/glm-5-3-flash) (open weights) | $0.15 | $0.50 | $0.03 | **$0.24** | 1M | 51.8 |
| [GLM-4.5-Air](https://noometry.com/models/glm-4-5-air) (open weights) | $0.20 | $1.10 | $0.03 | **$0.43** | 131K | 38.9 |
| [GLM-4.6V](https://noometry.com/models/glm-4-6v) (open weights) | $0.30 | $0.90 | — | **$0.45** | 128K | 41.3 |
| [GLM-5.3-FlashX](https://noometry.com/models/glm-5-3-flashx) (open weights) | $0.37 | $1.25 | $0.075 | **$0.59** | 1M | — |
| [GLM-4.5V](https://noometry.com/models/glm-4-5v) (open weights) | $0.60 | $1.80 | — | **$0.90** | 64K | 39.8 |
| [GLM-4.5](https://noometry.com/models/glm-4-5) (open weights) | $0.60 | $2.20 | $0.11 | **$1** | 131K | 42.0 |
| [GLM-4.6](https://noometry.com/models/glm-4-6) (open weights) | $0.60 | $2.20 | $0.11 | **$1** | 205K | 41.4 |
| [GLM-4.7](https://noometry.com/models/glm-4-7) (open weights) | $0.60 | $2.20 | $0.11 | **$1** | 205K | 42.0 |
| [GLM-5](https://noometry.com/models/glm-5) (open weights) | $1 | $3.20 | $0.20 | **$1.55** | 205K | 46.1 |
| [GLM-5-Turbo](https://noometry.com/models/glm-5-turbo) | $1.20 | $4 | $0.24 | **$1.90** | 200K | — |
| [GLM-5V-Turbo](https://noometry.com/models/glm-5v-turbo) | $1.20 | $4 | $0.24 | **$1.90** | 200K | 43.8 |
| [GLM-5.1](https://noometry.com/models/glm-5-1) (open weights) | $1.40 | $4.40 | $0.26 | **$2.15** | 200K | 47.8 |
| [GLM-5.2](https://noometry.com/models/glm-5-2) (open weights) | $1.40 | $4.40 | $0.26 | **$2.15** | 1M | 51.1 |
| [GLM-5.3](https://noometry.com/models/glm-5-3) (open weights) | $1.40 | $4.40 | $0.26 | **$2.15** | 1M | 54.8 |
| [GLM 5.3 Prime](https://noometry.com/models/glm-5-3-prime) | $2.80 | $8.80 | $0.56 | **$4.30** | 1M | — |

## Prices on other platforms

The same models are often sold through clouds and resellers at different rates.

| Model | Route | Input | Output | Checked |
| --- | --- | --- | --- | --- |
| [GLM-5.3](https://noometry.com/models/glm-5-3) | bedrock | $1.68 | $5.28 | 2026-10-10 |
|  | deepinfra | $0.90 | $4 | 2026-10-10 |
|  | fireworks | $1.40 | $4.40 | 2026-10-10 |
|  | mistral | $1.40 | $4.40 | 2026-10-10 |
|  | openrouter | $0.039 | $4.80 | 2026-10-10 |
|  | together | $1.40 | $4.40 | 2026-10-10 |
|  | zai | $1.40 | $4.40 | 2026-10-10 |
| [GLM-5.3-Flash](https://noometry.com/models/glm-5-3-flash) | deepinfra | $0.15 | $0.50 | 2026-10-10 |
|  | fireworks | $0.15 | $0.50 | 2026-10-10 |
|  | openrouter | $0.15 | $0.50 | 2026-10-10 |
|  | together | $0.15 | $0.50 | 2026-10-10 |
|  | zai | $0.15 | $0.50 | 2026-10-10 |
| [GLM-5.2](https://noometry.com/models/glm-5-2) | alibaba | $1.40 | $4.40 | 2026-10-10 |
|  | deepinfra | $0.75 | $2.40 | 2026-10-10 |
|  | mistral | $1.40 | $4.40 | 2026-10-10 |
|  | openrouter | $0.06 | $7 | 2026-10-10 |
|  | together | $1.40 | $4.40 | 2026-10-10 |
|  | vertex | $1.40 | $4.40 | 2026-10-10 |
|  | zai | $1.40 | $4.40 | 2026-10-10 |
| [GLM-5.1](https://noometry.com/models/glm-5-1) | deepinfra | $1.05 | $3.50 | 2026-10-10 |
|  | openrouter | $0.97 | $3.04 | 2026-10-10 |
|  | together | $1.40 | $4.40 | 2026-10-10 |
|  | zai | $1.40 | $4.40 | 2026-10-10 |
| [GLM-5](https://noometry.com/models/glm-5) | bedrock | $1 | $3.20 | 2026-10-10 |
|  | deepinfra | $0.60 | $2.08 | 2026-10-10 |
|  | openrouter | $0.60 | $1.92 | 2026-10-10 |
|  | together | $1 | $3.20 | 2026-10-10 |
|  | vertex | $1 | $3.20 | 2026-10-10 |
|  | zai | $1 | $3.20 | 2026-10-10 |
| [GLM-5V-Turbo](https://noometry.com/models/glm-5v-turbo) | openrouter | $1.20 | $4 | 2026-10-10 |
|  | zai | $1.20 | $4 | 2026-10-10 |
| [GLM-4.5](https://noometry.com/models/glm-4-5) | openrouter | $0.60 | $2.20 | 2026-10-10 |
|  | zai | $0.60 | $2.20 | 2026-10-10 |
| [GLM-4.7](https://noometry.com/models/glm-4-7) | bedrock | $0.60 | $2.20 | 2026-10-10 |
|  | deepinfra | $0.40 | $1.75 | 2026-10-10 |
|  | openrouter | $0.60 | $2.20 | 2026-10-10 |
|  | vertex | $0.60 | $2.20 | 2026-10-10 |
|  | zai | $0.60 | $2.20 | 2026-10-10 |
| [GLM-4.6](https://noometry.com/models/glm-4-6) | deepinfra | $0.50 | $2 | 2026-10-10 |
|  | openrouter | $0.50 | $2 | 2026-10-10 |
|  | zai | $0.60 | $2.20 | 2026-10-10 |
| [GLM-4.6V](https://noometry.com/models/glm-4-6v) | openrouter | $0.30 | $0.90 | 2026-10-10 |
|  | zai | $0.30 | $0.90 | 2026-10-10 |
| [GLM-4.5V](https://noometry.com/models/glm-4-5v) | openrouter | $0.60 | $1.80 | 2026-10-10 |
|  | zai | $0.60 | $1.80 | 2026-10-10 |
| [GLM-4.5-Air](https://noometry.com/models/glm-4-5-air) | openrouter | $0.13 | $0.85 | 2026-10-10 |
|  | zai | $0.20 | $1.10 | 2026-10-10 |
| [GLM-4.7-Flash](https://noometry.com/models/glm-4-7-flash) | bedrock | $0.07 | $0.40 | 2026-10-10 |
|  | deepinfra | $0.06 | $0.40 | 2026-10-10 |
|  | openrouter | $0.0605 | $0.40 | 2026-10-10 |
| [GLM-4.7-FlashX](https://noometry.com/models/glm-4-7-flashx) | zai | $0.07 | $0.40 | 2026-10-10 |
| [GLM-5.3-FlashX](https://noometry.com/models/glm-5-3-flashx) | openrouter | $0.37 | $1.25 | 2026-10-10 |
|  | zai | $0.37 | $1.25 | 2026-10-10 |
| [GLM 5.3 Prime](https://noometry.com/models/glm-5-3-prime) | openrouter | $2.80 | $8.80 | 2026-10-10 |
| [GLM-5-Turbo](https://noometry.com/models/glm-5-turbo) | openrouter | $1.20 | $4 | 2026-10-10 |
|  | zai | $1.20 | $4 | 2026-10-10 |

## Frequently asked questions

### How much does the Z.ai (Zhipu) API cost?

Z.ai (Zhipu) API prices run from $0.06 per million input tokens (GLM-4.7-Flash) to $2.80 (GLM 5.3 Prime). Its highest-ranked model, GLM-5.3, costs $1.40 input and $4.40 output per million tokens.

### Does Z.ai (Zhipu) discount cached input?

Yes. Cached input is billed at a lower rate on 15 of the 17 priced models; the cached rate is listed next to each model.