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 | $0.06/M | $1.20/M | 3.2 s | 61 tps | Read$0.06/M | — | +2 | 09/08/2026 | |||||
| 1M | $0.10/M | $0.50/M | 0.6 s | 34 tps | Read$0.10/M | — | +2 | 08/26/2026 | |||||
| 1M | $0.15/M | $7/M | 0.3 s | 152 tps | Read$0.14/M | — | +1 | 08/18/2026 | |||||
| 262K | $0.02/M | $4.35/M | 0.5 s | 85 tps | Read$0.02/M | — | +2 | 08/14/2026 | |||||
| 1M | $0.22/M | $0.84/M | 2.2 s | 90 tps | Read$0.13/M | — | +1 | 07/31/2026 | |||||
| 1M | $1/M | $14/M | 0.5 s | 88 tps | Read$0.40/M | — | +3 | 07/16/2026 | |||||
| 1M | $0.19/M | $8/M | 1.3 s | 172 tps | Read$0.18/M | — | +1 | 06/16/2026 | |||||
| 1M | $0.22/M | $0.84/M | 0.6 s | 79 tps | Read$0.13/M | — | 04/23/2026 |