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 | Web Search | Capabilities | ZDR | No Training | Regional Inference | Free Tier | Released |
|---|
| 1M | $0.30/M | $1.20/M | 1.7 s | 206 tps | Read$0.006/M | — | +1 | 09/08/2026 | |||||
| 1M | $1.12/M | $3.52/M | 1.8 s | 147 tps | Read$0.21/M | — | 08/18/2026 | ||||||
| 1M | $1.06/M | $3.17/M | 1.9 s | 67 tps | Read$0.04/M | — | 08/12/2026 | ||||||
| 1M | $0.35/M | $1.06/M | 2.3 s | 92 tps | Read$0.01/M | — | 07/31/2026 | ||||||
| 1M | $1.05/M | $3.30/M | 5.2 s | 58 tps | Read$0.20/M | — | 06/16/2026 | ||||||
| 1M | $0.15/M | $0.50/M | 7.2 s | 49 tps | Read$0.03/M | — | +1 | 08/26/2026 | |||||
| 262K | $2/M | $6/M | 1.6 s | 54 tps | Read$0.25/M Write$2.50/M | — | 08/03/2026 | ||||||
| 262K | $0.13/M | $0.52/M | 1.6 s | 185 tps | Read$0.03/M | — | 07/06/2026 | ||||||
| 1M | $0.60/M+1 more | $2.40/M+1 more | 0.7 s | 59 tps | Read$0.12/M | — | +1 | 05/31/2026 | |||||
| 1M | $0.35/M | $1.06/M | 21.6 s | 82 tps | Read$0.01/M | — | 04/23/2026 | ||||||
| 1.1M | $0.12/M | $0.24/M | 1.9 s | 42 tps | Read$0.0024/M | — | +1 | 04/22/2026 | |||||
| 1.1M | $0.30/M | $0.61/M | 2.9 s | 29 tps | Read$0.0025/M | — | 04/22/2026 | ||||||
| 1M | $0.13/M | $0.40/M | 0.9 s | 76 tps | — | — | +1 | 04/02/2026 | |||||
| 1M | $0.14/M | $0.40/M | — | — | Read$0.10/M | — | +1 | 04/02/2026 | |||||
| 197K | $0.30/M | $1.20/M | 1.3 s | 42 tps | Read$0.06/M | — | 03/18/2026 |