Wafer models
Fast open source LLMs for enterprise
| Model | Context | Input | Output | Latency | Throughput | Cache | Web Search | Capabilities | ZDR | No Training | Regional Inference | Free Tier | Released |
|---|
| 1M | $0.20/M | $0.60/M | 2.0 s | 59 tps | Read$0.06/M | — | +2 | 09/08/2026 | |||||
| 1M | $0.09/M | $0.35/M | 1.6 s | 64 tps | Read$0.03/M | — | +2 | 08/26/2026 | |||||
| 1M | $1.40/M | $4.40/M | 0.5 s | 147 tps | Read$0.26/M | — | +1 | 08/18/2026 | |||||
| 262K | $0.09/M | $4.40/M | 0.6 s | 103 tps | Read$0.09/M | — | +2 | 08/14/2026 | |||||
| 1M | $0.08/M | $0.35/M | 1.8 s | 120 tps | Read$0.06/M | — | +1 | 07/31/2026 | |||||
| 1M | $2.10/M | $10.95/M | 0.6 s | 25 tps | Read$0.21/M | — | +2 | 07/16/2026 | |||||
| 1M | $1.40/M | $4.40/M | 0.5 s | 108 tps | Read$0.26/M | — | +1 | 06/16/2026 | |||||
| 1M | $0.08/M | $0.35/M | 0.5 s | 116 tps | Read$0.06/M | — | 04/23/2026 |