| Output $/MTok | $8.00 | $15.00 | $1.00 |
|---|---|---|---|
| Input $/MTok | $2.00 | $2.50 | $1.00 |
| Cached input $/MTok | $0.5000 | $0.2500 | — |
| Context window | 1,047,576 | 1,050,000 | 128,000 |
| Output cap | 32,768 | 128,000 | 8,000 |
| Modalities | in: text, image / out: text | in: text, image / out: text | in: text / out: text |
| Tool use | ✓ | ✓ | — |
| Structured output | ✓ | ✓ | ✓ |
| Family | GPT-4.1 | GPT-5.4 | Sonar |
| Knowledge cutoff | 2024-06-01 | 2025-08-31 | — |
| Verified | 2026-07-19 | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |
| $/1M chars | $30.00 | $30.00 | $19.50 |
|---|---|---|---|
| Voice quality | neural | neural | neural |
| Voice cloning | — | — | — |
| Voice count | — | 94 | — |
| Languages | en, es, de, fr, nl, it, ja | en | 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 |
| SSML support | — | — | — |
| TTFB | — | 37ms | 200ms |
| Output formats | wav, mp3, linear16, mulaw, alaw, opus | — | pcm, mp3, wav, ulaw, alaw |
| Verified | 2026-07-19 | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |