| Output $/MTok | $4.40 | $15.00 | $6.00 |
|---|---|---|---|
| Input $/MTok | $1.10 | $3.00 | $1.20 |
| Cached input $/MTok | $0.2750 | $0.7500 | — |
| Context window | 200,000 | 131,072 | 262,144 |
| Output cap | 100,000 | 131,072 | 32,768 |
| Modalities | in: text, image / out: text | in: text / out: text | in: text / out: text |
| Tool use | ✓ | ✓ | ✓ |
| Structured output | ✓ | ✓ | ✓ |
| Family | o-series | Grok 3 | Qwen 3 Max |
| Knowledge cutoff | 2024-06-01 | 2024-11-30 | 2025-06-30 |
| Verified | 2026-07-19 | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ |
| $/min | $0.004800 |
|---|---|
| $/min batch | $0.004300 |
| Streaming | ✓ |
| Realtime | ✓ |
| Languages | en, en-US, en-AU, en-CA, en-GB, en-IE, en-IN, en-NZ |
| Diarization | extra-cost |
| TTFW | — |
| Verified | 2026-07-19 |
| Source | provider page ↗ |
| $/1M chars | $30.00 | $50.00 |
|---|---|---|
| Voice quality | neural | neural |
| Voice cloning | — | ✓ included |
| Voice count | 94 | — |
| Languages | en | 31+ |
| SSML support | — | — |
| TTFB | 37ms | — |
| Output formats | — | — |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |