| Output $/MTok | $1.00 | $6.00 | $6.00 |
|---|---|---|---|
| Input $/MTok | $1.00 | $2.00 | $1.20 |
| Cached input $/MTok | — | $0.3000 | — |
| Context window | 128,000 | 500,000 | 262,144 |
| Output cap | 8,000 | 500,000 | 32,768 |
| Modalities | in: text / out: text | in: text, image / out: text | in: text / out: text |
| Tool use | — | ✓ | ✓ |
| Structured output | ✓ | ✓ | ✓ |
| Family | Sonar | Grok 4 | Qwen 3 Max |
| Knowledge cutoff | — | 2026-02-01 | 2025-06-30 |
| Verified | 2026-07-19 | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |
| $/min | $0.002500 |
|---|---|
| $/min batch | — |
| Streaming | — |
| Realtime | — |
| Languages | 99+ |
| Diarization | extra-cost |
| TTFW | — |
| Verified | 2026-07-19 |
| Source | provider page ↗ |
| $/1M chars | $19.50 | $30.00 |
|---|---|---|
| Voice quality | neural | neural |
| Voice cloning | — | — |
| Voice count | — | 94 |
| Languages | 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 | en |
| SSML support | — | — |
| TTFB | 200ms | 37ms |
| Output formats | pcm, mp3, wav, ulaw, alaw | — |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |