GLM-4.7-Flash
Completely free, no daily quota limits. Loss leader for adoption. FlashX paid variant available at $0.07/$0.40 for higher throughput.
Data updated 2026-03-30
free OpenAI-compatible Function calling 128K context Released 2026-01
Pricing
| Type | USD / 1M tokens | CNY / 1M tokens |
|---|---|---|
| Input | Free | ¥0 |
| Output | Free | ¥0 |
| Cached Input | Free | ¥0 |
IDE Setup
Cursor
base_url: https://open.bigmodel.cn/api/paas/v4
model: glm-4.7-flash
Cline
base_url: https://open.bigmodel.cn/api/paas/v4
model: glm-4.7-flash
Strengths
- + completely free
- + no rate limit per day
- + good for prototyping
Watch Out For
- ! content censorship
- ! lower quality than GLM-5/4.7
International Access
Direct access: Yes
Latency from US: 200-400ms
Registration: account
Frequently Asked Questions
How much does GLM-4.7-Flash cost?
GLM-4.7-Flash is completely free — no cost for input or output tokens.
Can I use GLM-4.7-Flash from outside China?
Yes. GLM-4.7-Flash is directly accessible internationally. Registration requires account. Payment via .
Is GLM-4.7-Flash compatible with the OpenAI API?
Yes. GLM-4.7-Flash uses an OpenAI-compatible API. You can use any OpenAI SDK by changing the base URL to open.bigmodel.cn.
What is the context window of GLM-4.7-Flash?
GLM-4.7-Flash supports a 128K token context window (128,000 tokens).
How do I use GLM-4.7-Flash in Cursor or Cline?
Set the base URL to https://open.bigmodel.cn/api/paas/v4 and the model name to glm-4.7-flash. Both Cursor and Cline support OpenAI-compatible providers.
Related Articles & Guides
More from Zhipu AI
Ready to try GLM-4.7-Flash?
Get your API key from the official platform.
Go to Zhipu AI →