| Output $/MTok | $8.00 | $10.00 |
|---|---|---|
| Input $/MTok | $2.00 | $1.25 |
| Cached input $/MTok | $0.5000 | $0.1250 |
| Context window | 200,000 | 400,000 |
| Output cap | 100,000 | 128,000 |
| Modalities | in: text, image / out: text | in: text, image / out: text |
| Tool use | ✓ | ✓ |
| Structured output | ✓ | ✓ |
| Family | o-series | GPT-5 |
| Knowledge cutoff | 2024-06-01 | 2024-09-30 |
| Verified | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ |
| $/1M chars | $17.50 | $50.00 | $50.00 | $30.00 |
|---|---|---|---|---|
| Voice quality | neural | neural | neural | neural |
| Voice cloning | ✓ included | ✓ included | ✓ included | — |
| Voice count | 217 | — | — | 94 |
| Languages | en, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or | 31+ | 32+ | en |
| SSML support | — | — | — | — |
| TTFB | 200ms | — | 75ms | 37ms |
| Output formats | pcm, mp3, wav, ulaw, alaw | — | mp3_44100_128, pcm_16000, wav_44100, opus_48000_128, ulaw_8000, alaw_8000 | — |
| Verified | 2026-07-02 | 2026-07-02 | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ | provider page ↗ |