在GLM-4.6上进行迭代，引入了保留式推理和基于轮次的推理，以便在复杂的多轮任务中实现更稳定的执行。200K上下文。
兼容 OpenAI——沿用你现有的 SDK
https://api.orcarouter.ai/v1from openai import OpenAI
client = OpenAI(
base_url="https://api.orcarouter.ai/v1",
api_key="$ORCAROUTER_API_KEY",
)
response = client.chat.completions.create(
model="z-ai/glm-4.7",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)do_sampleinclude_reasoningmax_tokensreasoningrequest_idresponse_formatstopstreamtemperaturethinkingtool_choicetool_streamtoolstop_puser_id| 输入 / 1M tokens | $0.600 |
| 输出 / 1M tokens | $2.20 |
| 缓存读取 / 1M | $0.110 |
| 货币 | USD |
基于标价的估算
仅为估算——实际 Token 数取决于提供商的分词器。
@misc{orcarouter_glm_4_7,
title = {GLM 4.7 API},
author = {Z.ai},
year = {2025},
howpublished = {OrcaRouter},
url = {https://www.orcarouter.ai/models/z-ai/glm-4.7}
}Z.ai. (2025). GLM 4.7 API. OrcaRouter. https://www.orcarouter.ai/models/z-ai/glm-4.7