Fireworks models
Route requests to Fireworks through Vercel AI Gateway. Compare the models Fireworks 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 | $0.30/M | $1.20/M | 1.3 s | 215 tps | Read$0.006/M | — | +2 | US | 10/17/2026 | ||||
| 1M | $1.25/M | $4.25/M | 3.2 s | 113 tps | Read$0.15/M | — | +2 | US | 10/15/2026 | ||||
| 1M | $3/M | $15/M | 2.0 s | 68 tps | Read$0.30/M | — | +1 | 09/23/2026 | |||||
| 1M | $0.30/M | $1.20/M | 1.2 s | 151 tps | Read$0.006/M | — | +2 | US | 09/08/2026 | ||||
| 1M | $0.15/M | $0.50/M | 2.8 s | 143 tps | Read$0.03/M | — | +2 | US | 08/26/2026 | ||||
| 1M | $1.40/M | $4.40/M | 1.4 s | 94 tps | Read$0.26/M | — | +1 | US | 08/18/2026 | ||||
| 262K | $0.05/M | $0.20/M | 0.2 s | 584 tps | Read$0.01/M | — | +1 | 08/11/2026 | |||||
| 262K | $2/M | $6/M | 0.3 s | 198 tps | Read$0.25/M | — | +1 | 08/03/2026 | |||||
| 262K | $2/M | $6/M | 2.8 s | 150 tps | Read$0.25/M | — | +1 | 08/02/2026 | |||||
| 1M | $4.50/M | $22.50/M | — | — | Read$0.45/M | — | +3 | 07/27/2026 | |||||
| 1M | $3/M+1 more | $15/M+1 more | 2.1 s | 29 tps | Read$0.30/M | — | +3 | US | 07/16/2026 | ||||
| 262K | $0.60/M | $2.40/M | 0.3 s | 144 tps | Read$0.12/M | — | 06/04/2026 | ||||||
| 512K | $0.30/M | $1.20/M | 1.1 s | 167 tps | Read$0.06/M | — | +2 | 05/31/2026 | |||||
| 128K | $0.15/M | $0.60/M | 0.9 s | 177 tps | Read$0.02/M | — | +1 | 08/05/2025 |