| Output $/MTok | $8.00 |
|---|---|
| Input $/MTok | $2.00 |
| Cached input $/MTok | $0.5000 |
| Context window | 200,000 |
| Output cap | 100,000 |
| Modalities | in: text, image / out: text |
| Tool use | ✓ |
| Structured output | ✓ |
| Family | o-series |
| Knowledge cutoff | 2024-06-01 |
| Verified | 2026-05-17 |
| Source | provider page ↗ |
| $/min | $0.002500 | $0.004000 | $0.002500 |
|---|---|---|---|
| $/min batch | — | — | — |
| Streaming | ✓ | ✓ | — |
| Realtime | ✓ | ✓ | — |
| Languages | en | 55+ | 99+ |
| Diarization | extra-cost | included | extra-cost |
| TTFW | — | — | — |
| Verified | 2026-05-05stale 32d | 2026-05-19 | 2026-05-05stale 32d |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |
| $/1M chars | $50.00 | $50.00 |
|---|---|---|
| Voice quality | neural | neural |
| Voice cloning | ✓ included | ✓ included |
| Voice count | — | — |
| Languages | 15+ | 31+ |
| SSML support | — | — |
| TTFB | 90ms | — |
| Output formats | — | — |
| Verified | 2026-05-19 | 2026-05-19 |
| Source | provider page ↗ | provider page ↗ |