| Output $/MTok | $10.00 | $5.00 | $1.00 |
|---|---|---|---|
| Input $/MTok | $2.50 | $1.00 | $1.00 |
| Cached input $/MTok | $1.2500 | — | — |
| Context window | 128,000 | 1,048,576 | 128,000 |
| Output cap | 16,384 | 65,536 | 8,000 |
| Modalities | in: text, image / out: text | in: text / out: text | in: text / out: text |
| Tool use | ✓ | ✓ | — |
| Structured output | ✓ | ✓ | ✓ |
| Family | GPT-4o | Qwen 3 Coder | Sonar |
| Knowledge cutoff | 2023-10-01 | — | — |
| Verified | 2026-05-17stale 45d | 2026-05-19stale 43d | 2026-05-19stale 43d |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |
| $/1M chars | $25.00 | $30.00 | $30.00 |
|---|---|---|---|
| Voice quality | neural | neural | neural |
| Voice cloning | ✓ included | — | — |
| Voice count | 217 | 94 | — |
| Languages | en, hi, es, mr, kn, ta, bn, gu, te, ml, pa, or | en | en, es, de, fr, nl, it, ja |
| SSML support | — | — | — |
| TTFB | 200ms | 100ms | — |
| Output formats | pcm, wav, mp3, mulaw | — | wav, mp3, linear16, mulaw, alaw, opus |
| Verified | 2026-05-19stale 43d | 2026-05-19stale 43d | 2026-05-19stale 43d |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |