GLM 4.7 FlashX
GLM 4.7 FlashX is the ultra-fast inference variant in Z.AI's GLM-4.7 generation, released January 19, 2026. Designed for the lowest latency workloads, it provides the fastest response times in the GLM-4.7 family while retaining core coding and reasoning capabilities. Your use is subject to Z.AI's Terms & Privacy Policies.
ReasoningTool UseImplicit Caching
import { streamText } from 'ai'
const result = streamText({ model: 'zai/glm-4.7-flashx', prompt: 'Why is the sky blue?'})Copy link to headingMore models by Z.AI
| Model |
|---|
| 1M | 0.6s | 128tps | $0.15/M$0.08/M | $0.50/M$0.25/M | Read:$0.03/M$0.01/M Write:— | — | +1 |    +11 | 08/26/2026 | |||||
| 1M | 0.2s | 246tps | $1.40/M | $4.40/M | Read:$0.14/M Write:— | — | +7 | 08/18/2026 | ||||||
| 1M | 0.6s | 209tps | $2.10/M | $6.60/M | Read:$0.21/M Write:— | — |   | 06/23/2026 | ||||||
| 1M | 0.2s | 458tps | $0.70/MFast $2.10/M | $2.20/MFast $6.60/M | Read:$0.11/M Write:— | — |  +15 | 06/16/2026 | ||||||
| 205K | 1.5s | 59tps | $1.40/M | $4.40/M | Read:$0.26/M Write:— | — |   | 04/07/2026 | ||||||
| 203K | 0.7s | 120tps | $0.80/M | $2.56/M | Read:$0.16/M Write:— | — |  +1 | 02/12/2026 |