MiMo-V2.6-Flash

xiaomimimo/mimo-v2.6-flash

Xiaomi MiMo· 1.0M ctx

open weightstool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

1.0×

$0.250 – $0.350 · 5 providers · max÷min 1.4×

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	$0.100	$0.250	—	$0.114no cache price published
LLM Gateway router / aggregator	$0.120	$0.250	$0.00250	$0.0570
Kilo Gateway router / aggregator	$0.100	$0.280	$0.0500	$0.0845
NanoGPT router / aggregator	$0.140	$0.280	$0.00280	$0.0654
OpenCode Go subscription plan	$0.140	$0.280	$0.00280	$0.0654
OpenRouter router / aggregator	$0.140	$0.280	$0.00280	$0.0654
Requesty router / aggregator	$0.140	$0.280	$0.00270	$0.0654
Standard Compute router / aggregator	$0.140	$0.280	$0.00280	$0.0654
Tempr Gateway unclassified	$0.140	$0.280	$0.00280	$0.0654
Vercel AI Gateway router / aggregator	$0.140	$0.280	$0.00280	$0.0654
Novita AI inference host	$0.140	$0.280	$0.00280	$0.0654
Boundless unclassified	$0.140	$0.280	$0.00280	$0.0654
Deep Infra inference host	$0.140	$0.280	$0.00280	$0.0654
EmpirioLabs AI unclassified	$0.140	$0.280	$0.140	$0.153
Xiaomifirst-party first-party lab	$0.140	$0.280	$0.00280	$0.0654
AIHubMix router / aggregator	$0.155	$0.310	$0.00310	$0.0724
CrossModel router / aggregator	$0.160	$0.320	$0.00400	$0.0884
above.dev unclassified	$0.169	$0.339	$0.00340	$0.0791
Venice AIoutlier inference host	$0.175	$0.350	$0.00375	$0.0819

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

Unpriced · 2

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.

NaN mimo-v2.6-flashunpriced
OpenCode mimo-v2.6-flash-freeunpriced

Connect

Provider (default: cheapest output among direct providers)

$0.250 /M · inference host

opencode.json

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