Google Vertex AI models
Route requests to Google Vertex AI through Vercel AI Gateway. Compare the models Google Vertex 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 | $0.75/M | $3.75/M | 2.6 s | 144 tps | Read$0.08/M | $14/K+1 more | +3 | US EU | 09/02/2026 | ||||
| 1M | $0.75/M | $3.75/M | 3.0 s | 144 tps | Read$0.08/M | $14/K+1 more | +3 | US EU | 08/13/2026 | ||||
| 1M | $0.75/M | $3.75/M | 1.9 s | 118 tps | Read$0.08/M | $14/K+1 more | +3 | US EU | 07/21/2026 | ||||
| 1M | $10/M | $50/M | 8.6 s | 47 tps | Read$0.25/M Write$12.50/M | $10/K | +2 | 08/31/2026 | |||||
| 1M | $5/M | $25/M | 5.5 s | 76 tps | Read$0.50/M Write$6.25/M | $10/K | +3 | US EU | 07/24/2026 | ||||
| 1M | $0.30/M | $2.50/M | 0.7 s | 302 tps | Read$0.03/M | $14/K+1 more | +3 | US EU | 07/21/2026 | ||||
| 1M | $10/M | $50/M | 3.1 s | 99 tps | Read$1/M Write$12.50/M | $10/K | +2 | 07/01/2026 | |||||
| 66K | $0.25/M | $1.50/M+2 more | 0.6 s | — | Read$0.03/M | $14/K+1 more | +2 | 06/30/2026 | |||||
| 1M | $1.50/M+2 more | $9/M | — | — | — | — | +1 | 06/30/2026 | |||||
| 1M | $2/M | $10/M | 1.5 s | 102 tps | Read$0.20/M Write$2.50/M | $10/K | +3 | US EU | 06/29/2026 | ||||
| 1M | $5/M | $25/M | 1.1 s | 90 tps | Read$0.50/M Write$6.25/M | $10/K | +3 | US EU | 05/28/2026 | ||||
| 131K | $0.50/M | $3/M+5 more | 0.9 s | 230 tps | Read$0.05/M | $14/K+1 more | +1 | 05/28/2026 | |||||
| 1M | $1.50/M | $9/M | 2.2 s | 153 tps | Read$0.15/M | $14/K+1 more | +3 | US EU | 05/19/2026 | ||||
| 1M | $0.25/M | $1.50/M | 0.6 s | 205 tps | Read$0.03/M | $14/K+1 more | +3 | US EU | 05/07/2026 | ||||
| 1M | $1.25/M+1 more | $2.50/M+1 more | — | — | Read$0.20/M | $5/K | +2 | 04/30/2026 | |||||
| 1M | $5/M | $25/M | 1.0 s | 95 tps | Read$0.50/M Write$6.25/M | $10/K | +3 | US EU | 04/16/2026 | ||||
| 262K | $0.15/M | $0.60/M | 0.4 s | 35 tps | Read$0.02/M | — | +2 | 04/02/2026 | |||||
| — | — | $0.03/sec+1 more | — | — | — | — | 04/02/2026 | ||||||
| 2M | $2/M | $6/M | — | — | Read$0.20/M | — | +1 | 03/10/2026 | |||||
| 2M | $2/M | $6/M | — | — | Read$0.20/M | — | +3 | 03/10/2026 | |||||
| 1M | $2/M+1 more | $12/M+1 more | 6.8 s | 114 tps | Read$0.20/M | $14/K+1 more | +3 | 02/19/2026 | |||||
| 1M | $3/M | $15/M | 1.1 s | 51 tps | Read$0.30/M Write$3.75/M | $10/K | +3 | US EU | 02/17/2026 | ||||
| 1M | $5/M | $25/M | 1.8 s | 53 tps | Read$0.50/M Write$6.25/M | $10/K | +3 | US EU | 02/05/2026 | ||||
| 1M | $0.50/M+1 more | $3/M+1 more | 0.6 s | 128 tps | Read$0.05/M | $14/K+1 more | +3 | 12/17/2025 | |||||
| 200K | $5/M | $25/M | 1.0 s | 49 tps | Read$0.50/M Write$6.25/M | $10/K | +3 | US EU | 11/24/2025 | ||||
| 1M | $0.20/M | $0.50/M | — | — | Read$0.05/M | — | +1 | 11/19/2025 | |||||
| 1M | $0.20/M | $0.50/M | — | — | Read$0.05/M | — | +2 | 11/19/2025 | |||||
| 200K | $1/M | $5/M | 0.9 s | 105 tps | Read$0.10/M Write$1.25/M | $10/K | +3 | US EU | 10/15/2025 | ||||
| — | — | $0.20/sec+2 more | — | — | — | — | 10/15/2025 | ||||||
| — | — | $0.10/sec+2 more | — | — | — | — | 10/15/2025 | ||||||