DeepSeek V4 Pro 0813 vs Qwen3.5 397B A17B
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
- DeepSeek V4 Pro 0813 is 1.3× cheaper at a typical mix of 3 input tokens per output token.
- DeepSeek V4 Pro 0813 accepts longer prompts: 1M vs 262K tokens.
- DeepSeek V4 Pro 0813 output costs $0.80 per 1M via Sail Research, against the list price of $1.98.
- Qwen3.5 397B A17B output costs $2.34 per 1M via Alibaba, against the list price of $3.60.
- DeepSeek V4 Pro 0813 is the newer model (released 2026-08-12).
| DeepSeek V4 Pro 0813 | Qwen3.5 397B A17B | |
|---|---|---|
| Vendor | DeepSeek | Qwen |
| Released | 2026-08-12 | 2026-02-16 |
| Input / 1M | $0.66 | $0.50 |
| Output / 1M | $1.98 | $3.60 |
| Cached input / 1M | $0.022 | $0.30 |
| Blended / 1M (3:1) | $0.99 | $1.27 |
| Context | 1M | 262K |
| Max output | 393K | 236K |
| Accepts | text | text, image, video |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 26 | 10 |
| Cheapest provider, output | $0.80 | $2.34 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
DeepSeek V4 Pro 0813
$69.30 per month$2.31 per day
Qwen3.5 397B A17B
$84.00 per month$2.80 per day
DeepSeek V4 Pro 0813 saves $14.70 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V4 Pro 0813 with
Compare Qwen3.5 397B A17B with