DeepSeek V3.1 vs Qwen3.6 35B A3B
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- Qwen3.6 35B A3B is 1.4× cheaper at a typical mix of 3 input tokens per output token.
- Qwen3.6 35B A3B accepts longer prompts: 262K vs 164K tokens.
- Qwen3.6 35B A3B is the newer model (released 2026-04-27).
| DeepSeek V3.1 | Qwen3.6 35B A3B | |
|---|---|---|
| Vendor | DeepSeek | Qwen |
| Released | 2025-08-21 | 2026-04-27 |
| Input / 1M | $0.25 | $0.10 |
| Output / 1M | $0.95 | $0.90 |
| Cached input / 1M | $0.13 | $0.025 |
| Blended / 1M (3:1) | $0.425 | $0.30 |
| Context | 164K | 262K |
| Max output | 33K | 236K |
| Accepts | text | text, image, video |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 5 | 10 |
| Cheapest provider, output | $0.95 | $0.70 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
DeepSeek V3.1
$29.25 per month$0.97 per day
Qwen3.6 35B A3B
$19.50 per month$0.65 per day
Qwen3.6 35B A3B saves $9.75 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V3.1 with
Compare Qwen3.6 35B A3B with