Xiaomi models

Every Xiaomi model behind one OpenAI-compatible endpoint. You pay Xiaomi's published token rate — OrcaRouter adds $0. Below: live input, output and cached-input pricing per million tokens, context and output limits, measured latency, and the code to call any of them without changing your SDK.

Models
2
Cheapest input
$0.140 /M
Median p50
3250 ms
Max context
1M

Xiaomi API pricing

Xiaomi model pricing
ModelInput per million tokensOutput per million tokensCached in per million tokensContextMax outQualityTry
MiMo-V2.6-Pro$0.435$0.870$0.00361M131K9Try
MiMo-V2.6-Flash$0.140$0.280$0.00281M131K8Try

What it will cost you

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $5.66 · With prompt caching $4.15

Estimate based on list price

Estimating cost for MiMo-V2.6-Pro: $5.66 per month

Estimates use the provider's published rates. OrcaRouter adds $0 markup, so this is what you would pay calling them directly.

Call Xiaomi chat models

curl https://api.orcarouter.ai/v1/chat/completions \
  -H "Authorization: Bearer $ORCAROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.6-pro",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Already using the Xiaomi SDK? Point base_url at OrcaRouter and keep everything else.

Frequently asked

How much does the Xiaomi API cost through OrcaRouter?

Exactly the same as calling Xiaomi directly. MiMo-V2.6-Pro is $0.435 per million input tokens and $0.87 per million output tokens; the cheapest Xiaomi model here is MiMo-V2.6-Flash at $0.14 per million input. OrcaRouter adds $0 markup — you are billed the provider's published rate.

Can I bring my own Xiaomi key?

Yes. Add your own Xiaomi key in the console and OrcaRouter routes through it, so usage bills to your account with the provider while you keep the unified endpoint, logging, spend controls and automatic failover.

Do I need to change my SDK?

No. Point base_url at https://api.orcarouter.ai/v1, keep the OpenAI-compatible client you already use, and reference the model as xiaomi/<model>. Nothing else in your code changes.

Which Xiaomi model has the largest context window?

MiMo-V2.6-Pro, at 1048K tokens. The full context and max-output limits for every Xiaomi model are in the pricing table above.

How does Xiaomi compare with other providers?

Every model page carries side-by-side comparisons against the closest models from other providers on price, context, latency and benchmarks. Because OrcaRouter adds no markup, the prices you are comparing are the providers' own.

Which Xiaomi models support vision, tools or reasoning?

Across the Xiaomi catalogue: Vision (2), Audio (2), Tools (2), Reasoning (2), JSON mode (2). Use the capability chips above the pricing table to narrow the list to the models that support what you need.

Other providers

MiMo-V2.6-Pro · $0.435 /M inTry itGet an API key