GMICloud models
Route requests to GMICloud through Vercel AI Gateway. Compare the models GMICloud 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 | $0.18/M | $0.72/M | 1.1 s | 176 tps | Read$0.0036/M | — | +1 | 09/08/2026 | |||||
| 1M | $0.09/M | $0.30/M | 2.2 s | 60 tps | Read$0.02/M | — | +2 | 08/26/2026 | |||||
| 1M | $0.98/M | $3.08/M | 1.4 s | 134 tps | Read$0.18/M | — | +1 | 08/18/2026 | |||||
| 1M | $1.06/M | $3.17/M | 2.1 s | 80 tps | Read$0.04/M | — | +1 | 08/12/2026 | |||||
| 1M | $0.29/M | $0.86/M | 1.4 s | 173 tps | Read$0.0091/M | — | 07/31/2026 | ||||||
| 1.1M | $0.44/M | $0.87/M | 2.3 s | 42 tps | Read$0.004/M | — | +1 | 09/21/2026 | |||||
| 1.1M | $0.14/M | $0.28/M | 2.8 s | 32 tps | Read$0.003/M | — | +2 | 09/21/2026 | |||||
| 262K | $2/M | $6/M | 2.7 s | 51 tps | Read$0.25/M Write$2.50/M | — | 08/03/2026 | ||||||
| 262K | $0.14/M | $0.58/M | 1.8 s | 172 tps | Read$0.04/M | — | +1 | 07/06/2026 | |||||
| 1M | $1.40/M | $4.40/M | 1.7 s | 89 tps | Read$0.26/M | — | +1 | 06/16/2026 | |||||
| 1M | $0.24/M+1 more | $0.96/M+1 more | 1.5 s | 82 tps | Read$0.05/M | — | +2 | 05/31/2026 | |||||
| 1M | $0.29/M | $0.86/M | 3.3 s | 222 tps | Read$0.0091/M | — | +1 | 04/23/2026 | |||||
| 1.1M | $0.12/M | $0.24/M | 7.2 s | 28 tps | Read$0.0026/M | — | +2 | 04/22/2026 | |||||
| 1.1M | $0.30/M | $0.61/M | 1.8 s | 37 tps | Read$0.0028/M | — | +1 | 04/22/2026 | |||||
| 1M | $0.14/M | $0.40/M | — | — | Read$0.10/M | — | +1 | 04/02/2026 | |||||
| 1M | $0.13/M | $0.40/M | 1.0 s | 54 tps | — | — | +2 | 04/02/2026 | |||||
| 197K | $0.21/M | $0.84/M | 1.3 s | 41 tps | Read$0.04/M | — | 03/18/2026 |