| Output $/MTok | $1.50 | $8.00 | $1.00 | $6.00 |
|---|---|---|---|---|
| Input $/MTok | $0.25 | $2.00 | $1.00 | $2.00 |
| Cached input $/MTok | — | $0.5000 | — | $0.3000 |
| Context window | 1,048,576 | 200,000 | 128,000 | 500,000 |
| Output cap | 65,536 | 100,000 | 8,000 | 500,000 |
| Modalities | in: text, image, video / out: text | in: text, image / out: text | in: text / out: text | in: text, image / out: text |
| Tool use | ✓ | ✓ | — | ✓ |
| Structured output | ✓ | ✓ | ✓ | ✓ |
| Family | Qwen 3.6 Flash | o-series | Sonar | Grok 4 |
| Knowledge cutoff | — | 2024-06-01 | — | 2026-02-01 |
| Verified | 2026-07-19 | 2026-07-19 | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ | provider page ↗ |
| $/min | $0.003500 |
|---|---|
| $/min batch | — |
| Streaming | — |
| Realtime | — |
| Languages | en, es, fr, de, it, pt, ar, da, nl, fi, he, hi, ja, zh, no, sv, tr, vi |
| Diarization | extra-cost |
| TTFW | — |
| Verified | 2026-07-19 |
| Source | provider page ↗ |
| $/1M chars | $50.00 |
|---|---|
| Voice quality | neural |
| Voice cloning | ✓ included |
| Voice count | — |
| Languages | en, fr, de, es, pt, zh, ja, hi, ko |
| SSML support | — |
| TTFB | 40ms |
| Output formats | — |
| Verified | 2026-07-19 |
| Source | provider page ↗ |