GLM 4.6
ZhipuCompared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex...
| Ruta | Ent. | Sal. | Mixto | vs |
|---|---|---|---|---|
| $0.40 | $1.60 | $0.70 | - | |
| ● Venice fp4 | $0.43 | $1.75 | $0.76 | +9% |
| $0.55 | $2.20 | $0.96 | +37% | |
| ● Z.AI fp4 | $0.60 | $2.20 | $1.00 | +43% |
● API oficial · ● plataforma en la nube · ● host de inferencia · USD por 1M de tokens. Mismo modelo, distintos proveedores: el precio y la cuantización varían.
- Ctx
- 205K
- max output
- 131K
- cache read /1M
- $0.10
- Familia
- glm
- Modalidades
- text
- Funciones
- json · reasoning · tools
Precios en vivo, actualizados 2026-11-03.
| Modelo | Ent. | Sal. | Ctx |
|---|---|---|---|
| GLM 5.3 FlashX | $0.37 | $1.25 | 1.048576M |
| GLM 5.3 FlashX Legal | $0.37 | $1.25 | 1.048576M |
| GLM 4.6 · este modelo | $0.5 | $2 | 205K |
| GLM 5.3 | $0.08 | $3.6 | 1.048576M |
| GLM 4.7 | $0.6 | $2.2 | 205K |
| GLM 5 | $1 | $3.2 | 205K |