Qwen3.5 35B-A3B vs DeepSeek V4.1 Flash 1017 (Scaleway)
Qwen3.5 35B-A3B is cheaper on output tokens, while DeepSeek V4.1 Flash 1017 (Scaleway) offers a larger context window. Choose Qwen3.5 35B-A3B or DeepSeek V4.1 Flash 1017 (Scaleway) based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Qwen3.5 35B-A3B | DeepSeek V4.1 Flash 1017 (Scaleway) |
|---|---|---|
| Provider | Alibaba | Eden AI |
| Input / 1M tokens | $0.25 | $0.67 |
| Output / 1M tokens | $2.00 | $2.00 |
| Context window | 262K | 1M |
| Parameters | — | — |
| Open weights | Yes | Yes |
| Released | Feb 2026 | Oct 2026 |
| LMArena (Chatbot Arena) Elo score | 1395 | — |
| GPQA Diamond score | 83.5 | — |
| Epoch Capabilities Index score | 143 | — |
| LMArena WebDev Elo score | 1254 | — |
FAQ
Is Qwen3.5 35B-A3B or DeepSeek V4.1 Flash 1017 (Scaleway) cheaper?
Qwen3.5 35B-A3B is cheaper on output tokens ($2.00 vs $2.00 per 1M).
Which has the larger context window, Qwen3.5 35B-A3B or DeepSeek V4.1 Flash 1017 (Scaleway)?
DeepSeek V4.1 Flash 1017 (Scaleway) 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.