DeepInfra models
Route requests to DeepInfra through Vercel AI Gateway. Compare the models DeepInfra 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 | $0.08/M | $0.25/M | 2.2 s | 43 tps | Read$0.02/M | — | +1 | 08/26/2026 | |||||
| 1M | $0.22/M | $0.65/M | 0.6 s | 39 tps | Read$0.07/M | — | +1 | 08/21/2026 | |||||
| 262K | $0.06/M | $0.18/M | 0.4 s | 219 tps | Read$0.01/M | — | 08/27/2026 | ||||||
| 1M | $1.20/M | $4/M | 1.2 s | 53 tps | Read$0.12/M | — | 08/18/2026 | ||||||
| 262K | $0.40/M | $3/M | 13.6 s | 19 tps | Read$0.04/M | — | +1 | 08/14/2026 | |||||
| 1M | $1.30/M | $2.60/M | 0.3 s | 91 tps | Read$0.10/M | — | 08/12/2026 | ||||||
| 262K | $0.08/M | $0.20/M | 0.3 s | 107 tps | Read$0.04/M | — | 08/11/2026 | ||||||
| 256K | $1.65/M | $4.95/M | 1.6 s | 53 tps | Read$0.12/M | — | 08/03/2026 | ||||||
| 1M | $0.08/M | $0.18/M | 0.9 s | 46 tps | Read$0.02/M | — | 07/31/2026 | ||||||
| 1M | $0.58/M | $1.44/M | 0.5 s | 271 tps | Read$0.12/M | — | +2 | 07/30/2026 | |||||
| 1M | $2.85/M | $14.25/M | 0.7 s | 21 tps | Read$0.29/M | — | +2 | 07/16/2026 | |||||
| 262K | $0.14/M | $0.58/M | 0.3 s | 81 tps | Read$0.04/M | — | 07/06/2026 | ||||||
| 1M | $0.75/M | $2.40/M | 0.4 s | 108 tps | Read$0.14/M | — | 06/16/2026 | ||||||
| 262K | $0.74/M | $3.50/M | 0.5 s | 52 tps | Read$0.15/M | — | +1 | 06/12/2026 | |||||
| 262K | $0.50/M | $2.50/M | 1.1 s | 132 tps | Read$0.15/M | — | 06/04/2026 | ||||||
| 1M | $0.08/M | $0.18/M | 1.7 s | 47 tps | Read$0.02/M | — | 04/23/2026 | ||||||
| 66K | $1.74/M | $3.48/M | 0.4 s | 66 tps | Read$0.15/M | — | 04/23/2026 | ||||||
| 262K | $0.40/M | $2/M | 1.1 s | 21 tps | Read$0.08/M | — | +1 | 04/22/2026 | |||||
| 1M | $1/M | $3/M | 0.6 s | 40 tps | Read$0.20/M | — | 04/22/2026 | ||||||
| 203K | $1.40/M | $4.40/M | 8.1 s | 12 tps | Read$0.26/M | — | 04/07/2026 | ||||||
| 197K | $0.27/M | $0.95/M | 0.9 s | 48 tps | Read$0.03/M | — | 02/12/2026 | ||||||
| 262K | $0.09/M | $0.30/M | 0.2 s | 157 tps | Read$0.02/M | — | +1 | 01/29/2026 | |||||
| 203K | $0.43/M | $1.75/M | 0.6 s | 13 tps | Read$0.08/M | — | 12/22/2025 | ||||||
| 262K | $0.05/M | $0.24/M | 0.2 s | 149 tps | — | — | 12/15/2025 | ||||||
| 164K | $0.26/M | $0.38/M | 0.7 s | 10 tps | Read$0.13/M | — | 12/01/2025 | ||||||
| 164K | $0.26/M | $0.38/M | 0.7 s | 18 tps | Read$0.13/M | — | 12/01/2025 | ||||||
| 33K | $0.01/M | — | — | — | — | — | 11/14/2025 | ||||||
| 216K | $0.47/M | $2/M | 0.8 s | 34 tps | Read$0.14/M | — | 11/06/2025 | ||||||
| 131K | $0.20/M | $0.60/M | 1.2 s | 154 tps | — | — | 10/28/2025 | ||||||
| 203K | $0.50/M | $2/M | 1.3 s | 22 tps | Read$0.10/M | — | 09/30/2025 | ||||||