GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks.
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 | $1.68 | $1.55 | per 1M tokens |
| Outputper 1M tokens | $5.28 | $4.86 | per 1M tokens |
| Cached inputper 1M tokens | $0.31 | $0.29 | per 1M tokens |
What an agent paid per million tokens, by day.
Today · $1.68 in · $5.28 out per 1M 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 |
|---|---|---|
| StreamLakeFp8fp8, answering | 99.8% | 200K |
| ChutesFp8fp8, having trouble | 90.7% | 203K |
| DeepInfraFp4fp4, answering | 99.9% | 203K |
| SiliconFlowFp8fp8, answering | 99.9% | 205K |
| Phala, answering | 89.5% | 203K |
| AtlasCloudFp8fp8, answering | 98.5% | 203K |
| AlibabaFp8fp8, answering | 95.5% | 203K |
| NovitaFp8fp8, answering | 98.8% | 205K |
| NebiusFp8fp8, answering | 98.9% | 203K |
| BaiduFp8fp8, answering | 99.4% | 203K |
| GMICloudFp8fp8, answering | 98.4% | 203K |
| Friendli, answering | 100% | 203K |
| Z.AIFp8fp8, answering | 99.8% | 203K |
| VeniceFp8fp8, answering | 99.8% | 200K |