Qwen3.5 397B-A17B vs deepseek-ai/DeepSeek-V4-Pro
deepseek-ai/DeepSeek-V4-Pro is cheaper on output tokens, while deepseek-ai/DeepSeek-V4-Pro offers a larger context window. Choose Qwen3.5 397B-A17B or deepseek-ai/DeepSeek-V4-Pro based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3.5 397B-A17B | deepseek-ai/DeepSeek-V4-Pro |
|---|---|---|
| Provider | Alibaba | SiliconFlow (China) |
| Input / 1M tokens | $0.60 | $1.74 |
| Output / 1M tokens | $3.60 | $3.48 |
| Context window | 262K | 1M |
| Parameters | 397B | 1.6T |
| Open weights | Yes | Yes |
| Released | Feb 2026 | Apr 2026 |
| LMArena (Chatbot Arena) Elo score | 1438 | — |
| LMArena WebDev Elo score | 1400 | — |
| LMArena Vision Elo score | 1263 | — |
| GPQA Diamond score | 86.4 | — |
| Epoch Capabilities Index score | 147 | — |
FAQ
Is Qwen3.5 397B-A17B or deepseek-ai/DeepSeek-V4-Pro cheaper?
deepseek-ai/DeepSeek-V4-Pro is cheaper on output tokens ($3.48 vs $3.60 per 1M).
Which has the larger context window, Qwen3.5 397B-A17B or deepseek-ai/DeepSeek-V4-Pro?
deepseek-ai/DeepSeek-V4-Pro has the larger context window (1M tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.