Compare models
Up to four models side by side. The best value in each row is highlighted. Task scores are heuristics, not benchmark results.
| Attribute | ||
|---|---|---|
| Overview | ||
| Company | Alibaba (Qwen) | OpenAI |
| Version | 3.5 | — |
| Tier | balanced | fast |
| Released | 2026-02-25 | 2025-08-05 |
| Open weights | Yes | Yes |
| Parameters | 125.1B (10B active) | 117B (5.1B active) |
| Status | Active | Active |
| Pricing (USD per 1M tokens) | ||
| Input | $0.26 | $0.014 (best in this row) |
| Output | $2.08 | $0.052 (best in this row) |
| Cached input | — | $0.013 |
| Batch input | — | — |
| Batch output | — | — |
| Blended (3 in : 1 out) | $0.72 | $0.024 (best in this row) |
| Est. cost per token | $0.000000715 | $0.000000023 (best in this row) |
| Capacity | ||
| Context window | 262K (best in this row) | 131K |
| Max output | 66K | 66K |
| Inputs | image, text, video | text |
| Features | ||
| Caching | No | Yes |
| JSON schema | Yes | Yes |
| Reasoning | Yes | Yes |
| Tools | Yes | Yes |
| Task fit (heuristic, 1–5) | ||
| coding | 4 / 5 (best in this row) | 3 / 5 |
| reasoning | 4 / 5 (best in this row) | 3 / 5 |
| math | 4 / 5 (best in this row) | 3 / 5 |
| summarization | 4 / 5 | 4 / 5 |
| extraction | 4 / 5 | 4 / 5 |
| classification | 4 / 5 | 4 / 5 |
| chat | 4 / 5 (best in this row) | 3 / 5 |
| creative | 4 / 5 (best in this row) | 3 / 5 |
| translation | 4 / 5 | 4 / 5 |
| vision | 4 / 5 (best in this row) | 1 / 5 |
| long context | 3 / 5 | 3 / 5 |
| agentic | 4 / 5 (best in this row) | 3 / 5 |
Prices are USD per 1M tokens from vendor price lists. “—” means the vendor does not publish it.