MiMo-V2.6-Pro

xiaomimimo/mimo-v2.6-pro

Xiaomi MiMo· 1.0M ctx

open weightstool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

1.0×

$0.800 – $1.74 · 5 providers · max÷min 2.2×

5 providers priced · 5 offerings

Including routers & resellers

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 assumptionsInput : output: 1Cache-hit share of input%

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
Vultroutlier inference host	$0.400	$0.800	—	$0.436no cache price published
Kilo Gateway router / aggregator	$0.430	$0.870	$0.00360	$0.199
Requesty router / aggregator	$0.430	$0.870	$0.00360	$0.199
Standard Compute router / aggregator	$0.430	$0.870	$0.00360	$0.199
Deep Infra inference host	$0.430	$0.870	$0.00360	$0.199
EmpirioLabs AI unclassified	$0.435	$0.870	$0.435	$0.475
LLM Gateway router / aggregator	$0.435	$0.870	$0.00360	$0.200
NanoGPT router / aggregator	$0.435	$0.870	$0.00360	$0.200
Novita AI inference host	$0.435	$0.870	$0.00360	$0.200
OpenCode Go subscription plan	$0.435	$0.870	$0.00363	$0.200
OpenRouter router / aggregator	$0.435	$0.870	$0.00360	$0.200
Tempr Gateway unclassified	$0.435	$0.870	$0.00360	$0.200
Vercel AI Gateway router / aggregator	$0.435	$0.870	$0.00360	$0.200
Xiaomifirst-party first-party lab	$0.435	$0.870	$0.00360	$0.200
ZenMux router / aggregator	$0.435	$0.870	$0.00360	$0.200
Boundless unclassified	$0.435	$0.870	$0.00360	$0.200
CrossModel router / aggregator	$0.470	$0.940	$0.00500	$0.255
AIHubMix router / aggregator	$0.480	$0.960	$0.00384	$0.221
above.dev unclassified	$0.51	$1.02	$0.00420	$0.23
Neuralwattoutlier inference host	$0.87	$1.74	$0.04	$0.42

Subscription plans (flat fee, not per-token) · 5

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-v2.6-prosubscription plan
Xiaomi Token Plan (China) mimo-v2.6-proMainland-China endpointsubscription plan
Xiaomi Token Plan (Singapore) mimo-v2.6-prosubscription plan
DevPass (LLM Gateway) mimo-v2.6-prosubscription plan
ClinePass cline-pass/mimo-v2.6-prosubscription plan

Connect

Provider (default: cheapest output among direct providers)

$0.800 /M · inference host

opencode.json

{
  "provider": {
    "vultr": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.vultrinference.com/v1"
      },
      "models": {
        "mimo-v2.6-pro-rl": {}
      }
    }
  }
}

Set VULTR_API_KEY in your environment. Generated — verify against the OpenCode docs.

Not enough history yet — the min/median/max sparkline fills in as the daily snapshot accumulates.

Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.