Model · Xiaomi

Xiaomi MiMo-V2.6-Flash

Xiaomi MiMo-V2.6-Flash is served by Xiaomi through OpenRouter. It provides 1.05M tokens of context and supports text, vision, audio, video inputs.

Snapshot 2026-09-22 xiaomi/mimo-v2.6-flash

Context window

1.05M tokens

Input / 1M tokens

$0.140

Output / 1M tokens

$0.280

Key facts

Provider	Xiaomi
OpenRouter ID	`xiaomi/mimo-v2.6-flash`
Modalities	Text, Vision, Audio, Video
Best for	Budget, Multimodal

Source openrouter.ai/api/v1/models Verified 2026-09-22 Drift-checked daily 06:00 CST

Best-fit workloads

Best for budget

Low input/output cost for high-volume workloads.

Best multimodal

Handles images, files, audio or video inputs.

Cost estimates

These examples use the 2026-09-22 input and output prices. Cache discounts, provider surcharges and tool fees are excluded.

Workload	Input	Output	Estimated cost
Quick test	20,000	5,000	$0.004
Product chat month	500,000	125,000	$0.105
Document batch	5,000,000	1,000,000	$0.980

Strengths

✓ Same price as MiMo-V2.5 on a newer generation — the catalogue lists both at $0.14 in / $0.28 out per million
✓ 1.05M-token window with image, audio and video input
✓ The catalogue describes it as an open mixture-of-experts model, 309B parameters total with 15B active per token
✓ Cached input at $0.0028 per million, a hundredth of the fresh-input price

Limitations

! Listed 2026-09-21 and read 2026-09-22: no independent evaluation of it exists yet, and nothing here is a benchmark
! Output costs twice the input price per token, so long-form generation is where the bill lands
! The parameter count and architecture come from the vendor's own catalogue description

OpenRouter API quickstart

Run these examples from your server or edge function. Keep the OpenRouter API key private and do not expose it in browser code.

cURL

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.6-flash",
    "messages": [{ "role": "user", "content": "Summarize this document in five bullet points." }],
    "max_tokens": 500
  }'

JavaScript / TypeScript

const response = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "xiaomi/mimo-v2.6-flash",
    messages: [{ role: "user", content: "Summarize this document in five bullet points." }],
    max_tokens: 500,
  }),
});

const data = await response.json();
console.log(data.choices[0].message.content);

How to evaluate Xiaomi MiMo-V2.6-Flash

Run five real tasks from your product, not generic demo prompts.
Record token usage, latency and output quality.
Estimate cost using your real input/output mix.
Compare it against one model with a similar price and one stronger model.

Compare models View on OpenRouter ↗

Xiaomi MiMo-V2.6-Flash FAQ

What is Xiaomi MiMo-V2.6-Flash?

Xiaomi MiMo-V2.6-Flash is a Xiaomi model available through OpenRouter. It supports text, vision, audio, video inputs and is suited for budget, multimodal workloads.

How much does Xiaomi MiMo-V2.6-Flash cost on OpenRouter?

The 2026-09-22 snapshot lists $0.140 per 1M input tokens and $0.280 per 1M output tokens. Verify current pricing on OpenRouter before production.

How large is Xiaomi MiMo-V2.6-Flash's context window?

Xiaomi MiMo-V2.6-Flash offers 1.05M tokens of context in the current snapshot. Provider-specific limits and surcharges may apply.

Head-to-head comparisons

Xiaomi MiMo-V2.6-Flash vs Xiaomi MiMo-V2.6-Pro

Start on Flash and keep it unless your own evaluation shows Pro winning on the work you actually do. The only published number separating them is Pro's Artificial Analysis intelligence index of 46.3, and the catalogue carries no equivalent for Flash — so the tier difference is currently asserted rather than measured.

Xiaomi MiMo-V2.6-Flash vs DeepSeek V4 Flash

DeepSeek V4 Flash is cheaper to read and much dearer to write; since the repricing its output costs 16x its input, which makes it a reading model. MiMo-V2.6-Flash is the safer default because the two directions are priced within a factor of two of each other and it accepts media, so a workload that changes shape does not force a migration.

Pricing and context data are based on a 2026-09-22 snapshot. Provider limits can change; always verify on OpenRouter before production.