Xiaomi MiMo API
Xiaomi's API for its MiMo models, low-priced open-weight models with a 1M-token context and text, image, audio and video input, compatible with the OpenAI and Anthropic API formats.
Profile checked
- Oct 2026 Now covered: Xiaomi MiMo API, for llm api.
How makers use Xiaomi MiMo API
What Xiaomi MiMo API is used for
Xiaomi MiMo API vs the alternatives makers chose
| Option | Makers' products | 2026 launches | Free for | At 10,000 users | Open source | |
|---|---|---|---|---|---|---|
| 736 80% | 77% | ~1,000 users | $10/mo · GPT-6 Luna | No | ||
| 252 27% | 21% | ~1,000 users | $10/mo · Claude Haiku 5.5 | No | ||
| 99 11% | 12% | ~360 users | $28/mo · Gemini 3.1 Flash-Lite | No | ||
| 39 4% | 3% | ~1,500 users | $6.75/mo · GPT OSS 20B | No | ||
| 22 2% | 0% | — | — | No | ||
| 15 2% | 1% | ~1,700 users | $6.00/mo · Ministral 3 (3B) | No | ||
| Xiaomi MiMo API | 0 0% | 0% | ~1,000 users | — | No |
For LLM API: how many of the 923 makers' products we know the LLM API of chose each option, and the share among the 256 launched in 2026, since a tool that came first has products from every year, and what each costs at 10,000 users.
Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.
When to use Xiaomi MiMo API, and when not
Something else fits better if
- You want the strongest general models and the widest ecosystem of examples and integrations: OpenAI API or Claude or Gemini API.
- Token cost dominates your budget, for example high-volume batch or agent workloads: DeepSeek or Groq or Mistral AI.
- You want to try or mix many models with one key and one bill, and fall back when a provider is down: OpenRouter.
- You want that routing and spend control but self-hosted, with keys and logs on your servers: LiteLLM.
The Xiaomi MiMo API is Xiaomi's developer platform for its MiMo models. The current lineup is MiMo-V2.6-Pro, a 1-trillion-parameter mixture-of-experts flagship, the smaller and cheaper MiMo-V2.6-Flash, and an UltraSpeed version of Pro that Xiaomi says outputs up to 20 times faster. All take text, images, audio and video, have a 1M-token context window with up to 128K tokens of output, and support thinking mode, function calls, structured output and a built-in web search tool. Separate models cover speech recognition and text-to-speech.
More about Xiaomi MiMo API
There's no MiMo-specific SDK to learn. The API speaks the OpenAI Chat Completions format at https://api.xiaomimimo.com/v1, the Anthropic Messages format at https://api.xiaomimimo.com/anthropic, and a Responses API, so you use the official OpenAI or Anthropic SDKs, or agent tools such as Claude Code and Codex, by swapping the base URL and key. You sign in with a Xiaomi account and usage is deducted from a prepaid balance, billed in US dollars outside mainland China and in yuan inside it.
Useful for a small team: prices are low, from $0.14 / $0.28 per million input/output tokens on Flash; prompt caching is automatic, with cache hits at about 1% of the input price and cache writes currently free; a Batch API halves the price of Pro and Flash for work that can wait; and the Pro and Flash weights are released under the MIT license, so the same models can be hosted elsewhere. Unused balance can be refunded.
Limits: there's no free quota for the language models, and each account gets 100 requests and 10M tokens per minute per model, with UltraSpeed limits by arrangement. Older model names are retired on short notice: MiMo-V2.5 and V2.5-Pro stop working on October 21, 2026. The platform is run by Beijing Xiaomi Mobile Software Co., Ltd. under Chinese law; for mainland users data is stored in mainland China, and overseas users fall under separate terms. Xiaomi's privacy policy says it won't use the text you send for model training without your prior consent.
What Hacker News says about Xiaomi MiMo API
On Hacker News, 40% of comments about Xiaomi MiMo API recommend it and 0% criticize it: net praise +40%, the best liked of 12 tools HN discusses for LLM API.
By year
| Year | Comments choosing it, per month | Net praise |
|---|---|---|
| 2026 (8 mo) | 6.8 | +41% |
In their words
- “And now 100% to a mix of K3 / DeepSeek V4 / MiMo 2.5.” HN, Jul 2026
- “Or MiMo 2.5 Pro on the same OpenCode Go plan. 2 amazing models.” HN, Jun 2026
Hacker News comments January 2023 to August 2026 that name Xiaomi MiMo API in a sentence like "I use" or "we moved to", Claude read a sample of 33 and the counts scale it to all of them; net praise is comments recommending it minus comments criticizing it, as a share of all comments about it. How it's counted, and how HN compares with makers.
Who uses it
No maker's live product on record yet.
We haven't found a product that uses Xiaomi MiMo API yet.
None of these in makers' own words.
Alternatives to Xiaomi MiMo API
All alternatives by situation →Further reading
Questions makers ask about Xiaomi MiMo API
What are the alternatives to Xiaomi MiMo API?
For LLM API, the other options makers' products we track chose most are OpenAI API (736), Claude (252), Gemini API (99), Groq (39), Azure OpenAI (22), Mistral AI (15). Each alternative, with the situation it fits, is on the Xiaomi MiMo API alternatives page.
Where is my data processed?
Xiaomi's service agreement says that for service in mainland China, data is stored on servers in mainland China and not transferred out. Use outside mainland China falls under separate overseas terms, and you can contact Xiaomi to choose a data storage region, which may cost extra. source ↗
Does Xiaomi use my API inputs for training?
The MiMo platform privacy policy says Xiaomi won't use the text content you provide for model training or any other purpose without your prior consent. It doesn't say the same about images, audio or video. source ↗
Can I use the OpenAI or Anthropic SDK?
Yes. Use https://api.xiaomimimo.com/v1 as the base URL for the OpenAI SDK, or https://api.xiaomimimo.com/anthropic for the Anthropic SDK, with a MiMo API key (sk-…). Token Plan subscriptions use their own base URL and key. source ↗
Is there a free tier, and what are the rate limits?
There's no free quota for the language models; you pay per token from a prepaid balance (the text-to-speech models are free for a limited time). Each account gets 100 requests and 10M tokens per minute for each of V2.6-Pro and V2.6-Flash; UltraSpeed limits are set by arrangement. source ↗
Is there a cheaper rate for batch jobs?
Yes. The Batch API runs V2.6-Pro and V2.6-Flash asynchronously at half the real-time price, for example $0.07 / $0.14 per million input/output tokens on Flash. UltraSpeed isn't available in batch. source ↗
Can I run the models myself?
Yes. Xiaomi has released the weights of MiMo-V2.6-Pro and V2.6-Flash on Hugging Face under the MIT license, though Pro is a very large model at 1.02 trillion parameters (42B active). source ↗
How long do older models stay available?
Not long. MiMo-V2.5 and V2.5-Pro are retired at 10:00 Beijing time on October 21, 2026, after which those model names stop working. Xiaomi announces deprecations in advance by SMS, email and on its site. source ↗
Is Xiaomi MiMo API free?
No permanent free tier; paid use starts at Pay per token. source ↗
Is Xiaomi MiMo API open source or self-hostable?
Not open source, and hosted only.
Can AI coding agents work with Xiaomi MiMo API?
No llms.txt, official MCP server or CLI found yet.
Who uses Xiaomi MiMo API?
No tracked product yet. source ↗