Data as of 2026-09-20.
Price spread

MiMo-V2-Pro

xiaomimimo/mimo-v2-pro

Xiaomi MiMo· 1.0M ctx
API onlytool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$0.870 – $6.00 · 2 providers · max÷min 6.9×

2 providers priced · 2 offerings

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:
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.

ProviderInputOutputCache rdBlended
Xiaomifirst-party
first-party lab
$0.435$0.870$0.00360$0.200
ZenMuxtiered
router / aggregator
$1.00$3.00$0.20$0.67
OpenCode Gotiered
subscription plan
$1.00$3.00$0.20$0.67
Abacus
router / aggregator
$1.00$3.00$0.20$0.67
NovitaAItiered
inference host
$2.00$6.00$0.40$1.35
Subscription plans (flat fee, not per-token) · 3

Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.

  • Xiaomi Token Plan (Europe) mimo-v2-prosubscription plan
  • Xiaomi Token Plan (China) mimo-v2-proMainland-China endpointsubscription plan
  • Xiaomi Token Plan (Singapore) mimo-v2-prosubscription plan
Unpriced · 1

Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.

  • OpenCode Zen mimo-v2-pro-freeunpriced

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.