Xiaomi MiMo API pricing for every model, newest first
By TechCompare · Updated · How we check
MiMo-V2.6-Flash is the newest MiMo model and the lowest cost one Xiaomi sells for a 100,000 token prompt with a 5,000 token answer, at $0.00511 a call with three quarters of the input cached.
Every MiMo model and its API price
Newest first. Prices are per 1M tokens. One request is 100K tokens in and 5K out, with 75% of the input cached.
| Model | Input | Output | Cached | Context | One request | Listed |
|---|---|---|---|---|---|---|
| MiMo-V2.6-FlashXiaomi | $0.14 | $0.28 | $0.0028 | 1.05M | $0.0051 | Sep 21, 2026 |
| MiMo-V2.6-ProXiaomi | $0.435 | $0.87 | $0.0036 | 1.05M | $0.0155 | Sep 21, 2026 |
| MiMo-V2.6-Pro-UltraSpeedXiaomi | $4.35 | $8.70 | $0.036 | 1.05M | $0.1549 | Sep 21, 2026 |
| MiMo-V2.5Cheapest host: Venice | $0.40 | $2 | $0.08 | 1M | $0.026 | Apr 22, 2026 |
| MiMo-V2.5-ProCheapest host: AtlasCloud | $0.435 | $0.87 | $0.0036 | 1.02M | $0.0155 | Apr 22, 2026 |
Listed is the day OpenRouter added the model. Prices checked Nov 14, 2026.
MiMo is Xiaomi's model family, sold on Xiaomi's own MiMo platform. This page lists all 5 MiMo models OpenRouter carries, newest first, at Xiaomi's own price where Xiaomi sells the model and the host that charges least where it doesn't.
MiMo-V2.6-Pro is the flagship, with over a trillion parameters, at $0.435 input and $0.87 output per million tokens. MiMo-V2.6-Flash is open source, a mixture of experts model with 309B parameters and 15B active, at $0.14 and $0.28.
Calculator
Cost Comparison
Based on 100,000 input tokens (75% cached), 5,000 output tokens, and 100 requests.Prices come live from OpenRouter at each maker's own price where it's listed. Temporary deals are left out.
How to read the MiMo prices
UltraSpeed runs the same checkpoint as MiMo V2.6 Pro, with the same answer quality, at about ten times the speed. That speed costs extra. MiMo-V2.6-Pro-UltraSpeed bills $4.35 input and $8.70 output per million, 10 times the MiMo-V2.6-Pro output rate. Use it where a person waits on the answer, like chat or live coding, and keep background jobs on the normal model.
A cached token on MiMo-V2.6-Flash costs $0.0028 per million, 98% off the normal input rate, so a long agent session that resends its history pays the cached rate for most of it. MiMo-V2.6-Flash reads up to 1.05M tokens, the largest window in the family.
Because Flash is open source, you can also download it and run it yourself. With only 15B parameters active per token it's quick for its size, though you still need memory for all 309B.
Verdict
MiMo-V2.6-Flash is the newest MiMo model and the lowest cost one Xiaomi sells for the example request, so it's the first one to test. Move up to MiMo-V2.6-Pro only where Flash falls short.
Pick UltraSpeed only for the parts of your app where a person sits waiting. Everywhere else the normal speed does the same work.
More LLM pricing scenarios
Related guides
Frequently asked questions
How much does the MiMo API cost?
What is MiMo UltraSpeed?
Is MiMo open source?
Does the MiMo API cache prompts?
Which MiMo model has the largest context window?
Where do these prices come from?
Related tools
LLM VRAM Calculator
Calculate the VRAM needed to run or fine-tune any LLM at any quantization.
Use toolPower Cost Estimator
Estimate annual electricity costs for your PC, Server, or TV.
Use toolData Transfer Calculator
Estimate transfer times for files over USB, WiFi, Ethernet, and more.
Use toolJSON Formatter
Validate, format, and minify JSON. Browse it as a tree, run JSONPath queries, compare two documents, or validate against a JSON Schema.
Use tool