The cheapest any-modality model on this site — text, images, audio, and video in for $0.14 per million input tokens. Real rates for both MiMo models, a workload calculator, and the budget comparisons.
| MODEL | INPUT $/1M | CACHED IN | OUTPUT $/1M | BLENDED | CONTEXT | YOUR COST |
|---|---|---|---|---|---|---|
MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.435 | $0.0036 | $0.87 | $0.544 | 1.05M | $0.87 |
MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.14 | $0.0028 | $0.28 | $0.175 | 1.05M | $0.28 |
USD per 1M tokens from Xiaomi’s official pricing page as of October 16, 2026. Blended assumes a 3:1 input:output ratio.
MiMo-V2.6-Flash takes text, images, audio, and video — the full input surface — for $0.14 input / $0.28 output per 1M tokens with a 1M context and open weights (a 309B mixture-of-experts with 15B active). Few models offer audio and video input anywhere near this price; for voice and media pipelines on a budget it is essentially the default answer.
The September V2.6 release also retired the old naming trap. MiMo-V2.5-Pro was text-only; V2.6-Pro, a 1T+ parameter model at $0.435 / $0.87, takes the same four modalities as Flash. Pick Pro for harder reasoning and Flash for volume — modality no longer decides it.
Cache reads are nearly free on both — $0.0028 per 1M tokens on Flash and $0.0036 on Pro, under 2% of fresh input. These are Xiaomi’s own list prices from mimo.mi.com; the older V2.5 models are marked for retirement, so migrate pinned workloads.
MiMo-V2.6-Flash costs $0.14 input / $0.28 output per 1M tokens and MiMo-V2.6-Pro $0.435 / $0.87. Both take text, image, audio, and video input with a 1M-token context, and cache reads cost under 2% of fresh input.
Xiaomi publishes its rates on the MiMo platform at mimo.mi.com, and both models are also on OpenRouter under the xiaomi prefix — handy if you want one key across many vendors. V2.6-Flash ships open weights, so self-hosting is an option too.
V2.6-Pro is the larger, stronger model at about 3× the price; V2.6-Flash is the fast, cheap tier. Unlike the V2.5 generation — where Pro was text-only — both now take text, images, audio, and video, so pick by quality bar and budget.
On price per modality nothing touches V2.6-Flash: $0.18/1M blended with audio and video input included, versus $0.23 for Qwen3.8-Omni-Flash and $0.85 for Gemini Flash-Lite. For text-only work, GLM-5.3-Flash and Nemotron 3 Super compete at similar blended prices.
Also see: OpenAI API pricing · Claude API pricing · Gemini API pricing · Grok API pricing · DeepSeek API pricing · Kimi API pricing · GLM API pricing · MiniMax API pricing · all 68 models
ReqKey gives every key a credit balance — validate, deduct, enforce limits, and watch per-consumer MiMo spend in real time.