Z.ai
GLM 4.6
Released 2025-09-30 · Knowledge up to 2025-03-31
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...
You send / 1M
$0.550
tokens in
It replies / 1M
$2.20
tokens out
Memory
205K
tokens it can read at once
Typical request
$0.0018
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp4 | $0.400 | $1.60 | n/a | Read |
| Venice · fp4 | $0.430 | $1.75 | 100% | Read |
| DeepInfra · fp4 | $0.500 | $2.00 | 100% | Read |
| Novita · bf16 | $0.550 | $2.20 | 100% | Read |
| Z.AI · fp4 | $0.600 | $2.20 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: Yes
- Tool calling: Yes
- Longest reply: 131K tokens
- Repeated text is billed at $0.110 per 1M (prompt caching)
- Intelligence score: 18.5 / 100 (Artificial Analysis)
Similar models
Appears in
Top No-Training AI ModelsTop No-Training Zero Data Retention AI ModelsTop No-Training Zero Data Retention Reasoning AI ModelsTop No-Training Zero Data Retention Tool-Calling AI ModelsTop No-Training Reasoning AI ModelsTop No-Training Reasoning Tool-Calling AI ModelsTop No-Training Tool-Calling AI ModelsTop Zero Data Retention AI Models