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...
In
$0.50
Out
$2.00
Blended
$0.88
Where to buy this model
4 access routes| Route | In | Out | Blended | 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% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 205K
- max output
- 131K
- cache read /1M
- $0.10
- Family
- glm
- Modalities
- text
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
Zhipu models at a similar price
| Model | In | Out | 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 · this model | $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 |