| Model | Context | Latency | Throughput | Input | Output | Capabilities | Providers | ZDR | Released |
|---|
| 1M | 0.7s | 53tps | $3.00/M | $15.00/M | 02/17/2026 | ||||
| 1M | 0.6s | 191tps | $0.50/M | $3.00/M | 12/17/2025 | ||||
| 1M | 0.8s | 59tps | $5.00/M | $25.00/M | 02/05/2026 | ||||
| 2M | 0.5s | 95tps | $0.20/M | $0.50/M | 07/09/2025 | ||||
| 256K | 2.1s | 70tps | $0.03/M | $1.20/M | 10/24/2025 | ||||
| 205K | 3.4s | 61tps | $0.30/M | $1.20/M | 02/12/2026 | ||||
| 200K | 0.6s | 108tps | $1.00/M | $5.00/M | 10/25/2024 | ||||
| 1M | 0.3s | 267tps | $0.10/M | $0.40/M | 06/17/2025 | ||||
| 1.1M | 1.6s | 63tps | $2.50/M | $15.00/M | 03/05/2026 | ||||
| 262K | 0.4s | 180tps | $0.50/M | $2.80/M | +2 | 01/26/2026 | |||
| 1M | 1.3s | 209tps | $0.25/M | $1.50/M | 03/03/2026 | ||||
| 1M | 4.6s | 138tps | $2.00/M | $12.00/M | 02/19/2026 | ||||
| 131K | 0.3s | 971tps | $0.07/M | $0.30/M | +4 | 08/05/2025 | |||
| 1M | 0.8s | 56tps | $3.00/M | $15.00/M | 09/29/2025 | ||||
| 128K | 0.8s | 85tps | $1.25/M | $10.00/M | 11/12/2025 | ||||
| 205K | 3.4s | 47tps | $0.30/M | $1.20/M | 03/18/2026 | ||||
| 1M | 0.4s | 313tps | $0.30/M | $2.50/M | 03/20/2025 | ||||
| 200K | 0.9s | 56tps | $5.00/M | $25.00/M | 11/24/2024 | ||||
| 203K | 0.5s | 81tps | $0.80/M | $2.56/M | +3 | 02/12/2026 | |||
| 400K | 0.4s | 228tps | $0.75/M | $4.50/M | 03/17/2026 | ||||
| 128K | 0.5s | 52tps | $0.15/M | $0.60/M | 07/18/2024 | ||||
| 400K | 4.1s | 246tps | $0.25/M | $2.00/M | 08/07/2025 | ||||
| 400K | 1.0s | 75tps | $1.75/M | $14.00/M | 12/11/2025 | ||||
| 164K | 1.2s | 46tps | $0.28/M | $0.42/M | +1 | 12/01/2025 | |||
| 2M | 1.8s | 201tps | $0.20/M | $0.50/M | 07/09/2025 | ||||
| 400K | 0.6s | 57tps | $1.75/M | $14.00/M | 02/24/2026 | ||||
| 1M | 3.3s | 314tps | $2.00/M | $12.00/M | 11/18/2025 | ||||
| 400K | 6.0s | 412tps | $1.25/M | $10.00/M | 08/01/2025 | ||||
| 131K | 0.3s | 261tps | $0.35/M | $0.75/M | +5 | 08/05/2025 | |||
| 400K | 6.3s | 889tps | $0.05/M | $0.40/M | 08/07/2025 | ||||