| Output $/MTok | $9.00 | $1.00 |
|---|---|---|
| Input $/MTok | $1.50 | $1.00 |
| Cached input $/MTok | $0.1500 | — |
| Context window | 1,048,576 | 128,000 |
| Output cap | 65,536 | 8,000 |
| Modalities | in: text, image, audio, video / out: text | in: text / out: text |
| Tool use | ✓ | — |
| Structured output | ✓ | ✓ |
| Family | Gemini 3.5 | Sonar |
| Knowledge cutoff | 2025-01-31 | — |
| Verified | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ |
| $/1M chars | $50.00 | $30.00 | $30.00 | $50.00 |
|---|---|---|---|---|
| Voice quality | neural | neural | neural | neural |
| Voice cloning | ✓ included | — | — | ✓ included |
| Voice count | — | — | 94 | — |
| Languages | en, fr, de, es, pt, zh, ja, ko | en, es, de, fr, nl, it, ja | en | en, fr, de, es, pt, zh, ja, hi, ko |
| SSML support | — | — | — | — |
| TTFB | 90ms | — | 37ms | 40ms |
| Output formats | — | wav, mp3, linear16, mulaw, alaw, opus | — | — |
| Verified | 2026-07-02 | 2026-07-02 | 2026-07-02 | 2026-07-02 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ | provider page ↗ |