MiMo API

Every MiMo model on EmpirioLabs AI, 3 in all. Compare them, then call the one that fits your task, quality, and pricing needs.

Xiaomi Text Generation 3 models

About MiMo APIs

MiMo on EmpirioLabs brings together 3 model APIs from Xiaomi, including MiMo V2.6 Pro, MiMo V2.6 Flash, MiMo V2.6 Pro UltraSpeed. Each model keeps its own dedicated page with live pricing, parameters, docs, and playground access.

Use the same EmpirioLabs API key and endpoint pattern across the family, then switch behavior by changing the model id in your request.

MiMo models (3)

MiMo API pricing

Compare the family at a glance, then open a model page for the complete live rate card and parameters.

Per 1M tokens, by input rate

ModelInputOutput
MiMo V2.6 Flash$0.14$0.28
MiMo V2.6 Pro$0.435$0.87
MiMo V2.6 Pro UltraSpeed$4.35$8.70
Endpoint
POST/v1/chat/completions
Pricing
Type
Spec
Rate
Input
per 1M prompt tokens
$0.435
Output
per 1M generated tokens
$0.87
Web search
per call when invoked
$0.015
Best fit
Trillion-parameter flagship for agentic work, with native image, video, and audio understanding and reasoning across a 1M context.
Endpoint
POST/v1/chat/completions
Pricing
Type
Spec
Rate
Input
per 1M prompt tokens
$0.14
Output
per 1M generated tokens
$0.28
Web search
per call when invoked
$0.015
Best fit
Low-cost full-modality reasoner with native image, video, and audio understanding on a 1M context, built for high-frequency production workloads.
Endpoint
POST/v1/chat/completions
Pricing
Type
Spec
Rate
Input
per 1M prompt tokens
$4.35
Output
per 1M generated tokens
$8.70
Web Search (Linkup)
per call when invoked
$0.013
Best fit
High-throughput build of the trillion-parameter flagship, matching its full-modality reasoning while generating output substantially faster.
Compare every model on the full pricing page

How to call MiMo models

MiMo V2.6 Pro serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id mimo-v2-6-pro. For this family, swap the model value for any supported id: mimo-v2-6-pro mimo-v2-6-flash mimo-v2-6-pro-ultraspeed. Get an API key from the EmpirioLabs dashboard.

cURL
curl https://api.empiriolabs.ai/v1/chat/completions \
  -H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mimo-v2-6-pro",
    "messages": [
      {"role": "user", "content": "Write a haiku about the ocean."}
    ]
  }'

MiMo examples and comparisons

See prompt tests, output notes, and comparison runs that mention this model family.

MiMo APIs: common questions

What is the MiMo API?

MiMo on EmpirioLabs covers 3 model APIs from Xiaomi: MiMo V2.6 Pro, MiMo V2.6 Flash, MiMo V2.6 Pro UltraSpeed. You use one EmpirioLabs API key and choose the model id that fits the request.

Which MiMo model should I use?

Start with the model whose dedicated page matches your speed, quality, and pricing needs, then test it in the EmpirioLabs playground. The comparison cards above link to each model's live rate card and quickstart.

Can I switch between MiMo models without rebuilding my integration?

Yes. The family is designed around the same EmpirioLabs API pattern, so most integrations switch by changing the model value. Check the model page before shipping if you rely on a model-specific parameter.

How is MiMo pricing shown?

Pay as you go, or choose a plan with weekly allowances. The cards on this page show a short live-catalog summary, and each model page shows the complete rate card that matches API billing.

Which MiMo model costs the least on EmpirioLabs AI?

MiMo V2.6 Flash lists the lowest input rate of the 3 MiMo models priced that way, followed by MiMo V2.6 Pro, MiMo V2.6 Pro UltraSpeed. The price table on this page shows each model's lowest rate and what it applies to.

Can I try MiMo in the browser?

Yes. Open any model page in this family and use its playground link to test prompts and parameters in the browser before integrating the API.

Ready to use better endpoints?

Check out our pricing or reach out if you want your own model deployed on our stack.