GLM-4.7-Flash - Free Multilingual Model on Cloudflare, 131K Context
GLM-4.7-Flash - Free Multilingual Model on Cloudflare, 131K Context
Model ID
@cf/zai-org/glm-4.7-flash
Available on the Cloudflare Workers AI free plan, drawing from the 10,000 Neurons daily quota. The model is marked Zero data retention.
Model Information
| Property | Value |
|---|---|
| Context length | 131,072 tokens |
| Input price | $0 (within free quota) |
| Output price | $0 (within free quota) |
| Provider | Zhipu AI / Cloudflare |
| Status | Available on Workers Free |
| Input modalities | Text |
| Data retention | Zero retention |
| Multilingual | 100+ languages |
Description
GLM-4.7-Flash is Zhipu AI’s lightweight multilingual model, officially positioned for chat, instruction following, and multi-turn tool calling. It covers more than 100 languages and performs consistently well in Chinese.
In Cloudflare’s pricing it is the cheapest tier among the models covered here: about 5,500 Neurons per million input tokens and 36,400 Neurons per million output tokens. With the same 10,000 Neurons daily quota, GLM-4.7-Flash can handle noticeably more requests than Qwen 3.8 27B.
Usage Example
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \
-H "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{
"model": "@cf/zai-org/glm-4.7-flash",
"messages": [{"role": "user", "content": "Write a business email in Chinese for me"}]
}'Related Links
📚 Related Free Models
These models are also available for $0 on Cloudflare. Choose by context length and modality.
| Model | Context | Description |
|---|---|---|
| GPT-OSS 120B | 128K | OpenAI’s 120B open-weight reasoning model, available on |
| Qwen 3.8 27B | 262K | Alibaba’s 27B multimodal model with text and image input, |
📋 View all Cloudflare free models →
🔗 Site Navigation
Last updated on
· Source: Cloudflare official documentation and pricing pages. Quotas and prices may change at any time.