Baseten models
Route requests to Baseten through Vercel AI Gateway. Compare the models Baseten 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 | 1.2 s | 183 tps | Read$0.007/M | — | +2 | US | 09/08/2026 | ||||
| 1M | $2.10/M | $6.60/M | — | — | Read$0.21/M | — | +1 | US | 09/02/2026 | ||||
| 1M | $0.15/M | $0.50/M | 1.4 s | 29 tps | Read$0.03/M | — | +2 | US | 08/26/2026 | ||||
| 1M | $1.40/M+1 more | $4.40/M+1 more | 2.3 s | 92 tps | Read$0.14/M | — | +1 | US | 08/18/2026 | ||||
| 1M | $1.32/M | $3.96/M | 1.2 s | 71 tps | Read$0.13/M | — | +1 | US | 08/12/2026 | ||||
| 1M | $0.13/M | $0.26/M | 1.6 s | 270 tps | Read$0.03/M | — | +1 | US | 07/31/2026 | ||||
| 1M | $0.50/M | $1.20/M | 0.5 s | 293 tps | Read$0.10/M | — | +3 | US | 07/30/2026 | ||||
| 1M | $3/M | $15/M | 2.4 s | 105 tps | Read$0.30/M | — | +2 | US | 07/16/2026 | ||||
| 256K | $1/M | $4.05/M | 0.6 s | 249 tps | Read$0.17/M | — | +2 | US | 07/15/2026 | ||||
| 1M | $2.10/M | $6.60/M | — | — | Read$0.21/M | — | +1 | US | 06/23/2026 | ||||
| 1M | $1.40/M+1 more | $4.40/M+1 more | 1.8 s | 110 tps | Read$0.14/M | — | +1 | US | 06/16/2026 | ||||
| 256K | $0.95/M | $4/M | 0.8 s | 201 tps | Read$0.16/M | — | +3 | US | 06/12/2026 | ||||
| 1M | $0.60/M | $2.40/M | 0.7 s | 175 tps | Read$0.12/M | — | US | 06/04/2026 | |||||
| 1M | $1.32/M | $3.96/M | 2.1 s | 71 tps | Read$0.13/M | — | US | 04/23/2026 | |||||
| 1M | $0.13/M | $0.26/M | 0.6 s | 196 tps | Read$0.03/M | — | US | 04/23/2026 | |||||
| 262K | $0.95/M | $4/M | 0.5 s | 72 tps | Read$0.16/M | — | +2 | US | 04/20/2026 | ||||
| 200K | $0.60/M | $2.20/M | 0.6 s | 175 tps | Read$0.12/M | — | +1 | US | 12/22/2025 | ||||
| 131K | $0.10/M | $0.50/M | 0.3 s | 129 tps | — | — | US | 08/05/2025 |