Scan to join WeChat groupGLM-4.7-FlashX
GLM-4.7-FlashX: a glm-flash model from Zhipu AI, ~200K context, knowledge cutoff 2025-04
GLM-4.7-FlashX is a glm-flash model from Zhipu AI (~200K context, input around $0.07/1M tokens). Suitable for assistants, content generation, knowledge Q&A and business automation
starsCapabilities
codeFunction calling
paymentsContext and pricing
Context limit200,000
Max output131,072
Knowledge cutoff2025-04
Input price$0.07/ 1M tokens
Output price$0.4/ 1M tokens
Cached input price$0.01/ 1M tokens
descriptionOverview
Overview
GLM-4.7-FlashX is provided by Zhipu AI, model ID glm-4.7-flashx
Key specs
- Context: 200K tokens
- Max output: 131.1K tokens
- Knowledge cutoff: 2025-04
- Input price: $0.07/1M
- Output price: $0.4/1M
Best for
Consider GLM-4.7-FlashX when comparing context length, pricing, multimodal support and relay availability
lightbulbUse cases
- Assistants and customer support
- Content generation and rewriting
- Knowledge Q&A and summarization
- Structured extraction
thumb_upStrengths
- Very long context (~200K), good for long documents and codebases
- Open weights, can be self-hosted
- High single-response output limit (~131.1K)
infoLimitations
- Knowledge cutoff 2025-04; newer facts need external retrieval
- Pricing and availability vary by upstream and relay; verify with official docs and tests