GLM 4.6
z-ai/glm-4.6
- context
- 205K
- modalities
- text → text
- capabilities
- Tool use, Reasoning, Structured output, Low cost
Overview
Compared 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...
Providers
- DeepInfraView DeepInfra
- NovitaView Novita
- VeniceView Venice
- Z.AIView Z.AI
Access method depends on provider and account setup.
Pricing
| provider | input / 1M | output / 1M |
|---|---|---|
| DeepInfra | $0.50 | $2.00 |
| Novita | $0.55 | $2.20 |
| Venice | $0.43 | $1.75 |
| Z.AI | $0.60 | $2.20 |
DeepInfra
- input / 1M
- $0.50
- output / 1M
- $2.00
Novita
- input / 1M
- $0.55
- output / 1M
- $2.20
Venice
- input / 1M
- $0.43
- output / 1M
- $1.75
Z.AI
- input / 1M
- $0.60
- output / 1M
- $2.20
Use this model
through Nautili
Route requests to GLM 4.6 through your Nautili gateway using a supported SDK or the Nautili SDK.
Connect your stack to Nautili
Route across supported providers through one control layer.