| Output $/MTok | $10.00 | $1.00 |
|---|---|---|
| Input $/MTok | $2.50 | $1.00 |
| Cached input $/MTok | $1.2500 | — |
| Context window | 128,000 | 128,000 |
| Output cap | 16,384 | 8,000 |
| Modalities | in: text, image / out: text | in: text / out: text |
| Tool use | ✓ | — |
| Structured output | ✓ | ✓ |
| Family | GPT-4o | Sonar |
| Knowledge cutoff | 2023-10-01 | — |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |
| $/min | $0.003300 | $0.003000 |
|---|---|---|
| $/min batch | — | $0.001500 |
| Streaming | — | ✓ |
| Realtime | — | ✓ |
| Languages | en | 99+ |
| Diarization | included | unsupported |
| TTFW | — | — |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |
| $/1M chars | $19.50 | $50.00 |
|---|---|---|
| Voice quality | neural | neural |
| Voice cloning | — | ✓ included |
| Voice count | — | — |
| Languages | en, hi, mr, ta, ml, te, kn, pa, bn, or, gu, ar, zh, id, ja, ko, ms, tr, vi, de, es, fr, it, pt, ru, el, fi, no, pl | 42+ |
| SSML support | — | ✓ |
| TTFB | 200ms | 90ms |
| Output formats | pcm, mp3, wav, ulaw, alaw | raw/pcm_f32le, raw/pcm_s16le, raw/pcm_mulaw, raw/pcm_alaw, wav, mp3 |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |