SF·SIX / MODEL PROFILE
Z.ai GLM 4.6
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...
Z.ai GLM 4.6 costs $0.43 per 1M input tokens and $1.75 per 1M output tokens at the standard tier, the lowest default-region price among the 4 providers SF·SIX tracks, from Venice AI (fp4). On Z.ai (Zhipu)’s own API it costs $0.60 / $2.20. Cached input reads cost $0.08 per 1M tokens. Updated ; prices checked .
- Developer
- Z.ai (Zhipu)
- Input modalities
- text
- Output modalities
- text
- Context tokens
- 204,800
- Latest price observation
- 2026-10-17
- Lowest paired standard token quote
- $0.43 input / $1.75 output per 1M tokens
Dated price and provider records
| Provider and channel | Input | Output or native rate | Unit and status | Source and observation |
|---|---|---|---|---|
| Venice AIOpenRouter | $0.43 | $1.75 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepInfraOpenRouter | $0.50 | $2.00 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Novita AIOpenRouter | $0.55 | $2.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| Z.aiOpenRouter | $0.60 | $2.20 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
| DeepInfraOpenRouter · Flex tier | $0.40 | $1.60 | 1M tokenspriced · USD | OpenRouter2026-10-17 |
These are dated, non-executable observations. Verify the exact endpoint, price and terms with the source before use. Unknown values are not free.