Xiaomi: MiMo-V2.6-Flash.
MiMo-V2.6-Flash is Xiaomi's MIT-licensed 309B mixture-of-experts model, 15B active, taking text, image, video and audio with a 1M-token context for agent work.
2× AMD MI300X · $1.00/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
Variants in the MiMo family.
Xiaomi: MiMo-V2.6-Pro
MiMo-V2.6-Pro is Xiaomi's MIT-licensed mixture-of-experts model, 1.02T total ...
Xiaomi: MiMo-V2.6-Pro-UltraSpeed
MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship found...
Xiaomi: MiMo-V2-Flash
MiMo-V2-Flash is an open-source foundation language model developed by Xiaomi...
Xiaomi: MiMo-V2-Omni
MiMo-V2-Omni is a frontier omni-modal model that natively processes image, vi...
Xiaomi: MiMo-V2-Pro
MiMo-V2-Pro is Xiaomi's flagship foundation model, featuring over 1T total pa...
Xiaomi: MiMo-V2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agenti...
Xiaomi: MiMo-V2.5-Pro
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in ge...
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
1536 GB | $4.00/hr | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
768 GB | $2.00/hr | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
384 GB | $1.00/hr | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for Xiaomi: MiMo-V2.6-Flash across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like Xiaomi: MiMo-V2.6-Flash, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About Xiaomi: MiMo-V2.6-Flash.
MiMo-V2.6-Flash is the efficiency-balanced checkpoint of Xiaomi's MiMo-V2.6 series, with open weights under the MIT licence. It is a sparse mixture-of-experts model with 309B parameters in total and 15B active. One model takes text, images, video and audio, with a 1M-token context meant for long repositories, tool traces and multi-session agent runs. Xiaomi trained it with one mixed reinforcement-learning run across coding, general agents, visual tasks and cybersecurity. The series also has a Pro checkpoint.