How much does Z.ai: GLM-4.7-Flash (Free) cost on Ofox?

Z.ai: GLM-4.7-Flash (Free) on Ofox.ai costs $0/M per million input tokens and $0/M per million output tokens. Pay-as-you-go, no monthly fees.

What is Z.ai: GLM-4.7-Flash (Free)'s context window?

Z.ai: GLM-4.7-Flash (Free) supports a context window of 200,000 tokens, allowing you to process large documents and maintain long conversations.

How to use Z.ai: GLM-4.7-Flash (Free) API via Ofox?

Simply set your base URL to https://api.ofox.io/v1 and use your Ofox API key. The API is OpenAI-compatible — just change the base URL and API key in your existing code.

What capabilities does Z.ai: GLM-4.7-Flash (Free) support?

Z.ai: GLM-4.7-Flash (Free) supports the following capabilities: function calling, prompt caching, web search. Access all features through the Ofox.ai unified API.

此模型已下线

该模型已停止接受新请求,请改用其他可用的活跃模型。

Z.ai: GLM-4.7-Flash (Free)

Name: Z.ai: GLM-4.7-Flash (Free)
Brand: z-ai
Availability: InStock

Chat已下线

z-ai/glm-4.7-flash:free

对比开始使用

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding capabilities, long-horizon task planning, and tool collaboration, and has achieved leading performance among open-source models of the same size on several current public benchmark leaderboards.

上下文窗口

200K

最大输出 Token

128K

发布日期

2026-01-19

能力

函数调用提示缓存网络搜索

可用供应商

Zhipu

支持的协议

openaianthropic

定价

类型	价格
输入 Token	$0/M
输出 Token	$0/M
网络搜索	$0.01/R

代码示例

from openai import OpenAI

client = OpenAI(
    base_url="https://api.ofox.io/v1",
    api_key="YOUR_OFOX_API_KEY",
)

response = client.chat.completions.create(
    model="z-ai/glm-4.7-flash:free",
    messages=[
        {"role": "user", "content": "Hello!"}
    ],
)

print(response.choices[0].message.content)

第三方评测

LMArena ↗评测条目:glm-4.7-flash

Z.ai: GLM-4.7-Flash (Free) 在 LMArena 文本榜单(风格控制) 综合类别中获得 1368 分,在 374 个模型中排名第 162,基于 11,720 次人类偏好投票(更新于 2026-07-12)。

glm-4.7-flash 在 LMArena 的评测分数
类别	Arena 分数	95% 置信区间	排名	投票数
综合	1368	1362–1374	第 162 / 374 名	11,720
困难任务	1387	1379–1394	第 159 / 374 名	6,515
编程	1423	1412–1435	第 154 / 369 名	2,686
数学	1366	1345–1387	第 162 / 362 名	715
创意写作	1313	1299–1327	第 183 / 372 名	1,809
指令遵循	1351	1341–1361	第 167 / 374 名	3,171
中文	1434	1406–1461	第 120 / 344 名	442