# Z.ai

Z.ai serves 20 models on LLM API: 18 text models and 2 image models, all from Z.ai.

Model ID prefix: `zai/` · 20 models · [Z.ai privacy policy](https://docs.z.ai/legal-agreement/privacy-policy)
Updated: 2026-11-13
Canonical: https://llmapi.ai/providers/zai/

## Models and prices

Prices when Z.ai serves the request.

### Text (18)

Prices per 1M tokens.

| Model | Model ID | Input | Output | Cache read | Context |
| --- | --- | --- | --- | --- | --- |
| [GLM-5.3](https://llmapi.ai/models/zhipu-glm-5-3/) | `zai/glm-5.3` | $1.4 | $4.4 | $0.26 | 1M |
| [GLM 5.2](https://llmapi.ai/models/zhipu-zai-glm-5-2/) | `zai/zai-glm-5.2` | $1.4 | $4.4 | $0.26 | 1M |
| [GLM-5V-Turbo](https://llmapi.ai/models/z-ai-glm-5v-turbo/) | `zai/glm-5v-turbo` | $1.2 | $4 | $0.24 | 200K |
| [GLM-5.1](https://llmapi.ai/models/z-ai-glm-5-1/) | `zai/glm-5.1` | $1.4 | $4.4 | $0.26 | 203K |
| [GLM-5-Turbo](https://llmapi.ai/models/z-ai-glm-5-turbo/) | `zai/glm-5-turbo` | $1.2 | $4 | $0.24 | 200K |
| [GLM-5](https://llmapi.ai/models/z-ai-glm-5/) | `zai/glm-5` | $1 | $3.2 | $0.2 | 203K |
| [GLM-4.7](https://llmapi.ai/models/z-ai-glm-4-7/) | `zai/glm-4.7` | $0.6 | $2.2 | $0.11 | 205K |
| [GLM-4.7 FlashX](https://llmapi.ai/models/zhipu-glm-4-7-flashx/) | `zai/glm-4.7-flashx` | $0.07 | $0.4 | $0.01 | 200K |
| [GLM-4.6V FlashX](https://llmapi.ai/models/zhipu-glm-4-6v-flashx/) | `zai/glm-4.6v-flashx` | $0.04 | $0.4 | $0.004 | 128K |
| [GLM-4.6V](https://llmapi.ai/models/z-ai-glm-4-6v/) | `zai/glm-4.6v` | $0.3 | $0.9 | $0.055 | 131K |
| [GLM-4.6](https://llmapi.ai/models/z-ai-glm-4-6/) | `zai/glm-4.6` | $0.6 | $2.2 | $0.11 | 205K |
| [GLM-4.5V](https://llmapi.ai/models/zhipu-glm-4-5v/) | `zai/glm-4.5v` | $0.6 | $1.8 | $0.11 | 128K |
| [GLM-4.5](https://llmapi.ai/models/zhipu-glm-4-5/) | `zai/glm-4.5` | $0.6 | $2.2 | $0.11 | 128K |
| [GLM-4.5 X](https://llmapi.ai/models/zhipu-glm-4-5-x/) | `zai/glm-4.5-x` | $2.2 | $8.9 | $0.45 | 128K |
| [GLM-4.5 AirX](https://llmapi.ai/models/zhipu-glm-4-5-airx/) | `zai/glm-4.5-airx` | $1.1 | $4.5 | $0.22 | 128K |
| [GLM-4.5 Air](https://llmapi.ai/models/zhipu-glm-4-5-air/) | `zai/glm-4.5-air` | $0.2 | $1.1 | $0.03 | 128K |
| [GLM-4 32B (0414-128k)](https://llmapi.ai/models/zhipu-glm-4-32b-0414-128k/) | `zai/glm-4-32b-0414-128k` | $0.1 | $0.1 | — | 128K |
| [GLM-OCR](https://llmapi.ai/models/zhipu-glm-ocr/) | `zai/glm-ocr` | $0.0001 / page | — | — | 8K |

### Image (2)

Price per image.

| Model | Model ID | Price | Modes |
| --- | --- | --- | --- |
| [CogView-4](https://llmapi.ai/models/cogview-4/) | `zai/cogview-4` | $0.01 / image | Generate |
| [GLM-Image](https://llmapi.ai/models/zhipu-glm-image/) | `zai/glm-image` | $0.015 / image | Generate |

**Volume pricing.** At higher monthly volume, models on Z.ai may cost less. Book a call and sales will quote a price for your usage. [Book a call with sales](https://meetings.hubspot.com/julia-andriienko/llmapi) or [Create an account first](https://app.llmapi.ai/signup).

## Send requests to Z.ai

Put `zai/` before a model ID and the request goes to Z.ai. If Z.ai’s uptime over the last 5 minutes is below 90%, it goes to another provider of the model, unless it sends `X-No-Fallback: true`. [Routing docs](https://docs.llmapi.ai/features/routing)

Example: GLM-5.3, Chat Completions (`POST /v1/chat/completions`). Set LLMAPI_KEY to your LLM API key.

```python
import os

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

response = client.chat.completions.create(
    model="zai/glm-5.3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
```

Prices synced 2026-11-13.

Next step: [Get API key](https://app.llmapi.ai/signup)