Wafer models
Fast open source LLMs for enterprise
| Model | Context | Input | Output | Latency | Throughput | Cache | Search | Capabilities | ZDR | No Training | Regional Inference | Free AI Gateway Credit | Released |
|---|
| 1M | $0.07/M | $0.50/M | 0.9 s | 126 tps | Read$0.0065/M | — | +2 | US | 10/17/2026 | ||||
| 1M | $0.19/M | $0.65/M | 1.0 s | 182 tps | Read$0.01/M | — | +2 | — | 09/08/2026 | ||||
| 1M | $0.05/M | $0.20/M | 1.4 s | 33 tps | Read$0.05/M | — | +2 | — | 08/26/2026 | ||||
| 1M | $0.18/M | $1.40/M | 0.9 s | 94 tps | Read$0.18/M | — | +1 | US | 08/18/2026 | ||||
| 262K | $0.06/M | $2.30/M | 0.5 s | 78 tps | Read$0.06/M | — | +2 | — | 08/14/2026 | ||||
| 1M | $0.10/M | $0.23/M | 0.8 s | 155 tps | Read$0.10/M | — | +1 | — | 07/31/2026 | ||||
| 1M | $0.19/M | $20/M | 1.3 s | 64 tps | Read$0.18/M | — | +3 | US | 07/16/2026 | ||||
| 1M | $0.19/M | $8/M | 1.3 s | 169 tps | Read$0.18/M | — | +1 | US | 06/16/2026 | ||||
| 1M | $0.10/M | $0.23/M | 0.3 s | 222 tps | Read$0.10/M | — | — | 04/23/2026 |