Z.AI models
Route requests to Z.AI through Vercel AI Gateway. Compare the models Z.AI serves, with unified billing and automatic failover across providers.
| Model | Context | Input | Output | Latency | Throughput | Cache | Search | Capabilities | ZDR | No Training | Regional Inference | Free AI Gateway Credit | Released |
|---|
| 1M | $0.37/M | $1.25/M | 1.0 s | 137 tps | Read$0.08/M | — | +2 | — | 11/02/2026 | ||||
| 1M | $0.37/M | $1.25/M | 6.1 s | 112 tps | Read$0.08/M | — | +2 | — | 09/18/2026 | ||||
| 1M | $0.15/M | $0.50/M | 1.4 s | 44 tps | Read$0.03/M | — | +2 | — | 08/26/2026 | ||||
| 1M | $1.40/M | $4.40/M | 4.1 s | 107 tps | Read$0.26/M | — | +1 | — | 08/18/2026 | ||||
| 1M | $1.40/M | $4.40/M | 0.8 s | 154 tps | Read$0.26/M | — | +1 | — | 06/16/2026 | ||||
| 203K | $1.40/M | $4.40/M | 3.1 s | 46 tps | Read$0.26/M | — | +1 | — | 04/07/2026 | ||||
| 200K | $1.20/M | $4/M | 0.7 s | 93 tps | Read$0.24/M | — | +3 | — | 04/01/2026 | ||||
| 203K | $1.20/M | $4/M | 3.7 s | 61 tps | Read$0.24/M | — | — | 03/15/2026 | |||||
| 203K | $1/M | $3.20/M | 0.8 s | 103 tps | Read$0.20/M | — | +1 | — | 02/12/2026 | ||||
| 200K | $0.07/M | $0.40/M | 41.9 s | 121 tps | Read$0.01/M | — | +1 | — | 01/19/2026 | ||||
| 200K | $0.06/M | $0.40/M | 0.9 s | 146 tps | Read$0.01/M | — | — | 01/19/2026 | |||||
| 200K | $0.60/M | $2.20/M | 3.7 s | 61 tps | Read$0.11/M | — | +1 | — | 12/22/2025 | ||||
| 200K | $0.60/M | $2.20/M | 3.9 s | 45 tps | Read$0.11/M | — | +1 | — | 09/30/2025 | ||||
| 66K | $0.60/M | $1.80/M | 0.7 s | 110 tps | Read$0.11/M | — | +2 | — | 08/11/2025 | ||||
| 128K | $0.20/M | $1.10/M | 0.6 s | 91 tps | Read$0.03/M | — | +1 | — | 07/28/2025 | ||||
| 128K | $0.60/M | $2.20/M | 3.7 s | 61 tps | Read$0.11/M | — | +1 | — | 07/28/2025 |