Qwen3.5-122B-A10B vs Xiaomi MiMo-V2.5
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 1.1× cheaper at a typical mix of 3 input tokens per output token.
- MiMo-V2.5 accepts longer prompts: 1M vs 262K tokens.
- MiMo-V2.5 output costs $0.238 per 1M via GMICloud, against the list price of $2.00.
- Qwen3.5-122B-A10B's best provider was more reliable over 24 h: 99.76% vs 99.03%.
- MiMo-V2.5 is the newer model (released 2026-04-22).
| Qwen3.5-122B-A10B | MiMo-V2.5 | |
|---|---|---|
| Vendor | Qwen | Xiaomi |
| Released | 2026-02-25 | 2026-04-22 |
| Input / 1M | $0.26 | $0.40 |
| Output / 1M | $2.08 | $2.00 |
| Cached input / 1M | — | $0.08 |
| Blended / 1M (3:1) | $0.715 | $0.80 |
| Context | 262K | 1M |
| Max output | 66K | 66K |
| Accepts | text, image, video | text, image, audio, video |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 4 | 2 |
| Cheapest provider, output | $2.08 | $0.238 |
| Best provider uptime, 24 h | 99.76% | 99.03% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
Qwen3.5-122B-A10B
$46.80 per month$1.56 per day
MiMo-V2.5
$54.00 per month$1.80 per day
Qwen3.5-122B-A10B saves $7.20 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare Qwen3.5-122B-A10B with