DeepSeek R1 0528 vs Qwen3.5-122B-A10B
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
- Qwen3.5-122B-A10B is 1.3× cheaper at a typical mix of 3 input tokens per output token.
- Qwen3.5-122B-A10B accepts longer prompts: 262K vs 164K tokens.
- R1 0528's best provider was more reliable over 24 h: 100% vs 97.9%.
- Qwen3.5-122B-A10B is the newer model (released 2026-02-25).
| R1 0528 | Qwen3.5-122B-A10B | |
|---|---|---|
| Vendor | DeepSeek | Qwen |
| Released | 2025-05-28 | 2026-02-25 |
| Input / 1M | $0.50 | $0.26 |
| Output / 1M | $2.15 | $2.08 |
| Cached input / 1M | $0.35 | — |
| Blended / 1M (3:1) | $0.912 | $0.715 |
| Context | 164K | 262K |
| Max output | 33K | 66K |
| Accepts | text | text, image, video |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 3 | 4 |
| Cheapest provider, output | $2.15 | $2.08 |
| Best provider uptime, 24 h | 100% | 97.9% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
R1 0528
$62.25 per month$2.08 per day
Qwen3.5-122B-A10B
$46.80 per month$1.56 per day
Qwen3.5-122B-A10B saves $15.45 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare R1 0528 with
Compare Qwen3.5-122B-A10B with