GLM-5.2 是面向长任务时代的旗舰模型。支持真正可用的 1M 上下文,实测可承载项目级工程上下文,长程任务执行更稳定、工程规范遵循更可靠,开发场景成功率进一步提升。一次任务即可完成“从需求到多端可部署产物”的完整开发链路。
from openai import OpenAI
client = OpenAI(
base_url="https://api.openroute.cn/v1",
api_key="<ONTOROUTE_API_KEY>",
)
completion = client.chat.completions.create(
model="z-ai/glm-5.2",
messages=[
{
"role": "user",
"content": "Write a one-sentence bedtime story about a unicorn.",
}
],
)
print(completion.choices[0].message.content)暂无调用数据
Prices are CNY (¥) per million tokens, billed as you go. Cache reads can cut the cost of repeated context.
| Provider | Input | Output | Cache read | Context length | Latency | Uptime | Status |
|---|---|---|---|---|---|---|---|
volcengine glm-5-2-260617 | ¥8.00 | ¥28.00 | Supported | 1M | 4.3s | 91.70% | Lowest |
z-ai z-ai/glm-5.2 | ¥8.00 | ¥28.00 | Supported | 1M | 1.0s | 0.00% |
| Parameter | Description | Default |
|---|---|---|
| tools | Tools | Set per request |
| presence_penalty | Presence penalty | Set per request |
| frequency_penalty | Frequency penalty | Set per request |
| max_tokens | Max tokens | Set per request |
| top_k | Top K | Set per request |
| top_p | Top P | Set per request |
| temperature | Temperature | Set per request |