MiMo-V2.6-Pro-UltraSpeed
xiaomimimo/mimo-v2.6-pro-ultraspeed
Xiaomi MiMo· 1.0M ctx
open weightstool callreasoning quant: unknown
spread (output, p90 ÷ p10)
— too few providers
$8.70 – $8.70 · 1 providers · max÷min 1.0×
1 provider priced · 1 offering
Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.
Blended $/M assumptions
blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published
A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
Xiaomifirst-party first-party lab | $4.35 | $8.70 | $0.04 | $2.00 |
Tempr Gateway unclassified | $4.35 | $8.70 | $0.04 | $2.00 |
Vercel AI Gateway router / aggregator | $4.35 | $8.70 | $0.04 | $2.00 |
EmpirioLabs AI unclassified | $4.35 | $8.70 | $4.35 | $4.75 |
Kilo Gateway router / aggregator | $4.35 | $8.70 | $0.04 | $2.00 |
NanoGPT router / aggregator | $4.35 | $8.70 | $0.04 | $2.00 |
OpenRouter router / aggregator | $4.35 | $8.70 | $0.04 | $2.00 |
AIHubMix router / aggregator | $4.80 | $9.60 | $0.04 | $2.21 |
above.dev unclassified | $5.08 | $10.15 | $0.04 | $2.33 |
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.