Qwen3-VL 235B A22B Thinking vs Kimi K2.5
Qwen3-VL 235B A22B Thinking is cheaper on output tokens, while Kimi K2.5 offers a larger context window. Choose Qwen3-VL 235B A22B Thinking or Kimi K2.5 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3-VL 235B A22B Thinking | Kimi K2.5 |
|---|---|---|
| Provider | Merge Gateway | Merge Gateway |
| Input / 1M tokens | $0.29 | $0.60 |
| Output / 1M tokens | $2.87 | $3.00 |
| Context window | 131K | 262K |
| Parameters | — | 1T |
| Open weights | Yes | Yes |
| Released | Sep 2025 | Jan 2026 |
FAQ
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.