| Model | Context | Latency | Throughput | Input | Output | Capabilities | Providers | ZDR | Released |
|---|
| 1M | 0.8s | 160tps | $0.50/M | $3.00/M | 12/17/2025 | ||||
| 1M | 2.5s | 66tps | $5.00/M | $25.00/M | 02/05/2026 | ||||
| 256K | 2.3s | 64tps | $0.03/M | $1.20/M | 10/24/2025 | ||||
| 1M | 1.2s | 84tps | $3.00/M | $15.00/M | 02/17/2026 | ||||
| 1M | 0.2s | 248tps | $0.10/M | $0.40/M | 06/17/2025 | ||||
| 400K | 2.1s | 59tps | $1.75/M | $14.00/M | 12/11/2025 | ||||
| 200K | 0.4s | 106tps | $1.00/M | $5.00/M | 10/25/2024 | ||||
| 262K | 0.6s | 87tps | $0.50/M | $2.80/M | +2 | 01/26/2026 | |||
| 205K | 2.7s | 53tps | $0.30/M | $1.20/M | 02/12/2026 | ||||
| 1M | 5.4s | 173tps | $2.00/M | $12.00/M | 02/19/2026 | ||||
| 1M | 0.7s | 73tps | $3.00/M | $15.00/M | 09/29/2025 | ||||
| 200K | 0.6s | 55tps | $3.00/M | $15.00/M | 01/25/2024 | ||||
| 1M | 1.0s | 55tps | $3.00/M | $15.00/M | 05/22/2025 | ||||
| 200K | 1.0s | 49tps | $5.00/M | $25.00/M | 11/24/2024 | ||||
| 1M | 0.5s | 310tps | $0.30/M | $2.50/M | 03/20/2025 | ||||
| 128K | 0.7s | 50tps | $0.15/M | $0.60/M | 07/18/2024 | ||||
| 164K | 1.1s | 33tps | $0.26/M | $0.38/M | 12/01/2025 | ||||
| 128K | 1.0s | 109tps | $1.25/M | $10.00/M | 11/12/2025 | ||||
| 2M | 0.9s | 92tps | $0.20/M | $0.50/M | 07/09/2025 | ||||
| 400K | 3.4s | 165tps | $1.75/M | $14.00/M | 02/24/2026 | ||||
| 400K | 5.1s | 330tps | $0.25/M | $2.00/M | 08/07/2025 | ||||
| 2M | 5.6s | 157tps | $0.20/M | $0.50/M | 07/09/2025 | ||||
| 400K | 6.6s | 585tps | $0.05/M | $0.40/M | 08/07/2025 | ||||
| 1M | 0.4s | 138tps | $0.15/M | $0.60/M | 12/11/2024 | ||||
| 256K | 0.3s | 142tps | $0.20/M | $1.50/M | 08/28/2025 | ||||
| 400K | 2.6s | 191tps | $1.75/M | $14.00/M | 12/18/2025 | ||||
| 131K | 0.2s | 1536tps | $0.25/M | $0.69/M | +5 | 08/05/2025 | |||
| 400K | 5.7s | 464tps | $1.25/M | $10.00/M | 08/01/2025 | ||||
| 205K | 0.9s | 208tps | $0.43/M | $1.75/M | 12/22/2025 | ||||
| 256K | 0.9s | 77tps | 12/09/2025 | ||||||