| Output $/MTok | $10.00 | $0.90 | $6.00 | $1.00 |
|---|---|---|---|---|
| Input $/MTok | $2.50 | $0.30 | $1.20 | $1.00 |
| Cached input $/MTok | $1.2500 | — | — | — |
| Context window | 128,000 | 131,072 | 262,144 | 128,000 |
| Output cap | 16,384 | 8,192 | 32,768 | 8,000 |
| Modalities | in: text, image / out: text | in: text / out: text | in: text / out: text | in: text / out: text |
| Tool use | ✓ | ✓ | ✓ | — |
| Structured output | ✓ | ✓ | ✓ | ✓ |
| Family | GPT-4o | Codestral | Qwen 3 Max | Sonar |
| Knowledge cutoff | 2023-10-01 | — | 2025-06-30 | — |
| Verified | 2026-07-19 | 2026-07-19 | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ | provider page ↗ | provider page ↗ |
| $/min | $0.003300 | $0.005800 |
|---|---|---|
| $/min batch | — | $0.009200 |
| Streaming | — | ✓ |
| Realtime | — | ✓ |
| Languages | en | 61+ |
| Diarization | included | extra-cost |
| TTFW | — | — |
| Verified | 2026-07-19 | 2026-07-19 |
| Source | provider page ↗ | provider page ↗ |