GLM 5.1
ZhipuGLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interactions, GLM-5.1 can work independently and continuously on...
| Rota | Ent. | Saí. | Misto | vs |
|---|---|---|---|---|
| ● Chutes mais baratofp8 | $0.90 | $2.90 | $1.40 | - |
| ● StreamLake fp8 | $0.97 | $3.04 | $1.48 | +6% |
| ● SiliconFlow fp8 | $1.19 | $3.74 | $1.83 | +31% |
| ● AtlasCloud fp8 | $1.26 | $3.96 | $1.94 | +39% |
| ● Phala | $1.21 | $4.20 | $1.96 | +40% |
| ● Alibaba fp8 | $1.33 | $4.18 | $2.04 | +46% |
| $1.38 | $4.40 | $2.13 | +52% | |
| $1.40 | $4.40 | $2.15 | +54% | |
| ● Baidu fp8 | $1.40 | $4.40 | $2.15 | +54% |
| $1.40 | $4.40 | $2.15 | +54% | |
| ● Friendli | $1.40 | $4.40 | $2.15 | +54% |
| ● Z.AI fp8 | $1.40 | $4.40 | $2.15 | +54% |
| ● Venice fp8 | $1.40 | $4.40 | $2.15 | +54% |
● API oficial · ● plataforma de nuvem · ● host de inferência · USD por 1M de tokens. Mesmo modelo, provedores diferentes — preço e quantização variam.
- Ctx
- 205K
- max output
- 131K
- cache read /1M
- $0.26
- Família
- glm
- Modalidades
- text
- Recursos
- json · reasoning · tools
Preços ao vivo, atualizados 2026-11-03.
| Modelo | Ent. | Saí. | Ctx |
|---|---|---|---|
| GLM 5 | $1 | $3.2 | 205K |
| GLM 5.2 | $0.006 | $6.8 | 1.048576M |
| GLM 5 Turbo | $1.2 | $4 | 203K |
| GLM 5V Turbo | $1.2 | $4 | 203K |
| GLM 5.1 · este modelo | $1.4 | $4.4 | 205K |
| GLM 5.3 Prime | $2.8 | $8.8 | 1M |