Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →lingtai-ai/xiaomi-mimo
Nested swiss-knife reference for Xiaomi MiMo provider discovery. Discovery protocol (not a reference) for Xiaomi MiMo (小米MiMo) — an OpenAI-/Anthropic-compatible LLM provider whose single API key unlocks a family of ~9 models behind one chat-completions endpoint. The family spans long-context text reasoning, multimodal-input chat (image / audio / video understanding via standard `messages.content[]`), and a text-to-speech line that returns base64 audio (with built-in voice catalogue, voice-design
Passed 14 of 18 test cases with the skill, and 8 of 18 without it.
and 11 more in the full report
9 fixed8 passed either way3 still failing2 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.
On a local workstation, in which directory does Lingtai TUI store custom preset manifests, and in which file does it store secret API keys for Xiaomi MiMo?
| Checked | Without skill | With skill |
|---|---|---|
| Identifies ~/.lingtai-tui/presets/ for storing preset manifest JSON files | Missed | Passed |
| Identifies ~/.lingtai-tui/.env for storing environment key variables | Missed | Passed |
The instructions your model reads when the skill loads.
This is a discovery protocol, not a reference. It teaches you where to look for current MiMo capabilities — it does not mirror them. Anything API-shaped (model IDs, request schemas, voice catalogues, quotas) drifts faster than this manual; fetch the live docs every time.
Two URLs and an LLM-friendly bulk dump are all the agent needs to bootstrap full knowledge of the API:
| Purpose | URL |
|---|---|
| Doc index (start here for any specific question) | platform.xiaomimimo.com/llms.txt |
| Full doc dump (one curl → every public doc page concatenated) | platform.xiaomimimo.com/llms-full.txt |
| Marketing / model gallery (skim once for the vibe) | mimo.xiaomi.com |
# Quick orientation — what doc pages exist right now?
curl -s https://platform.xiaomimimo.com/llms.txt | head -60
# Full dump — when you need everything in context (much larger)
curl -s https://platform.xiaomimimo.com/llms-full.txt | wc -l
The doc index is structured so you can grep for what you need (e.g. grep -i tts, grep -i pricing, grep -i multimodal). Each entry has a verbatim URL — fetch the specific page once you've located it.
Enough context for the agent to know what kind of question to ask the docs. Verify model IDs and capability claims against the live docs every time — Xiaomi rotates suffixes and adds new variants regularly.
Three rough families share one https://<host>/v1/chat/completions endpoint:
type: "image_url" | "input_audio" | "video_url") alongside text. Output is text. Use for transcription, image OCR, scene description, audio-visual joint reasoning, etc.To get the current exact model IDs and per-model capability matrix:
# Inspect the OpenAI-compat spec — lists every model the endpoint accepts
curl -s https://platform.xiaomimimo.com/static/docs/api/chat/openai-api.md | head -200
test cases passed, vs 8 / 18 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.