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 | Web Search | Capabilities | ZDR | No Training | Regional Inference | Free Tier | Released |
|---|
| 1M | $0.37/M | $1.25/M | 3.4 s | 152 tps | Read$0.08/M | — | +1 | 09/18/2026 | |||||
| 1M | $0.15/M | $0.50/M | 6.0 s | 53 tps | Read$0.03/M | — | +1 | 08/26/2026 | |||||
| 1M | $1.40/M | $4.40/M | 5.5 s | 86 tps | Read$0.26/M | — | 08/18/2026 | ||||||
| 1M | $1.40/M | $4.40/M | 1.1 s | 96 tps | Read$0.26/M | — | 06/16/2026 | ||||||
| 203K | $1.40/M | $4.40/M | 6.4 s | 43 tps | Read$0.26/M | — | 04/07/2026 | ||||||
| 200K | $1.20/M | $4/M | 0.9 s | 47 tps | Read$0.24/M | — | +2 | 04/01/2026 | |||||
| 203K | $1.20/M | $4/M | 3.7 s | 67 tps | Read$0.24/M | — | 03/15/2026 | ||||||
| 203K | $1/M | $3.20/M | 1.0 s | 196 tps | Read$0.20/M | — | 02/12/2026 | ||||||
| 200K | $0.06/M | $0.40/M | 0.8 s | 120 tps | Read$0.01/M | — | 01/19/2026 | ||||||
| 200K | $0.07/M | $0.40/M | 0.9 s | 194 tps | Read$0.01/M | — | 01/19/2026 | ||||||
| 200K | $0.60/M | $2.20/M | 3.8 s | 68 tps | Read$0.11/M | — | 12/22/2025 | ||||||
| 200K | $0.60/M | $2.20/M | 4.1 s | 46 tps | Read$0.11/M | — | 09/30/2025 | ||||||
| 66K | $0.60/M | $1.80/M | 0.9 s | 53 tps | Read$0.11/M | — | +1 | 08/11/2025 | |||||
| 128K | $0.20/M | $1.10/M | 0.7 s | 89 tps | Read$0.03/M | — | 07/28/2025 | ||||||
| 128K | $0.60/M | $2.20/M | 4.0 s | 67 tps | Read$0.11/M | — | 07/28/2025 |