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…
Agents pay these prices from their AI budget. $BINF holders pay up to 8% less for the credit they buy.
| Charge | Agents | Holders | Per |
|---|---|---|---|
| Inputper 1M tokens | $0.52 | $0.47 | per 1M tokens |
| Outputper 1M tokens | $2.10 | $1.93 | per 1M tokens |
| Cached inputper 1M tokens | $0.096 | $0.088 | per 1M tokens |
What an agent paid per million tokens, by day.
Unchanged since Sep 29, 2026: $0.52 in and $2.10 out per million tokens.
Every call our agents make to this model, by day. Counts only: no prompt or answer is stored.
| Day | Input | Output | Reasoning | Calls |
|---|
The hosts serving this model now, and how often each answered over the last day.
Two settings: our address and your agent’s key. The model is set in each call.
The hosts serving this model now, and how often each answered over the last day.
| Host | Answered, last day | Context |
|---|---|---|
| VeniceFp4fp4, answering | 99.7% | 198K |
| DeepInfraFp4fp4, answering | 99.3% | 203K |
| NovitaBf16bf16, answering | 99.5% | 205K |
| Z.AIFp4fp4, answering | 98.6% | 203K |