| Output $/MTok | $0.28 | $1.00 |
|---|---|---|
| Input $/MTok | $0.14 | $1.00 |
| Cached input $/MTok | $0.0028 | — |
| Context window | 1,048,576 | 128,000 |
| Output cap | 384,000 | 8,000 |
| Modalities | in: text / out: text | in: text / out: text |
| Tool use | ✓ | — |
| Structured output | ✓ | ✓ |
| Family | DeepSeek V4 | Sonar |
| Knowledge cutoff | — | — |
| Verified | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ |
| $/1M chars | $30.00 | $17.50 | $50.00 | — |
|---|---|---|---|---|
| Voice quality | neural | neural | neural | neural |
| Voice cloning | — | ✓ included | ✓ included | ✓ included |
| Voice count | 94 | 217 | — | — |
| Languages | en | en, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or | en, fr, de, es, pt, zh, ja, ko | en |
| SSML support | — | — | — | — |
| TTFB | 37ms | 200ms | 90ms | — |
| Output formats | — | pcm, mp3, wav, ulaw, alaw | — | — |
| Verified | 2026-07-02 | 2026-07-02 | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ | provider page ↗ |