Configure OpenAI-compatible or Anthropic-compatible clients to use MiMo models on RunAPI.
Model Reference | Skill Repo | All Models
Call MiMo through RunAPI with Chat Completions, Responses, or Messages. Point
OpenAI-compatible clients at https://runapi.ai/v1, use mimo-v2.5-pro or
mimo-v2.5, and keep billing on one RunAPI balance. This skill teaches Claude
Code, Codex, Gemini CLI, Cursor, and 50+ agents how to configure MiMo clients.
The canonical agent file is skills/mimo/SKILL.md.
npx skills add runapi-ai/mimo -gOr paste this prompt to your AI agent:
Install the mimo skill for me:
1. Clone https://github.com/runapi-ai/mimo
2. Copy the skills/mimo/ directory into your
user-level skills directory (e.g. ~/.claude/skills/
for Claude Code, ~/.codex/skills/ for Codex).
3. Verify that SKILL.md is present.
4. Confirm the install path when done.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_RUNAPI_TOKEN",
base_url="https://runapi.ai/v1",
)
response = client.chat.completions.create(
model="mimo-v2.5-pro",
messages=[{"role": "user", "content": "Draft a concise answer."}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
apiKey: "YOUR_RUNAPI_TOKEN",
baseURL: "https://runapi.ai/v1",
});
const response = await client.responses.create({
model: "mimo-v2.5",
input: "Summarize this report.",
});
console.log(response.output_text);Get a RunAPI API Key at https://runapi.ai/api_keys.
mimo-v2.5 accepts HTTP(S) image URLs in synchronous Chat Completions requests:
response = client.chat.completions.create(
model="mimo-v2.5",
messages=[{
"role": "user",
"content": [
{"type": "text", "text": "Describe this image."},
{
"type": "image_url",
"image_url": {
"url": "https://cdn.runapi.ai/public/samples/image.jpg"
},
},
],
}],
stream=False,
)
print(response.choices[0].message.content)| Model ID | Notes |
|---|---|
mimo-v2.5-pro |
Higher-quality MiMo text generation |
mimo-v2.5 |
Efficient MiMo text generation |
- Basic text supports sync and SSE on Chat Completions, Responses, and Messages.
mimo-v2.5supportstextand HTTP(S)image_urlparts on synchronous Chat Completions requests.- Tools, reasoning controls, continuation state, documents, audio, video, data
URL images, streaming image requests, and image input on
mimo-v2.5-pro, Responses, or Messages are rejected before usage is reserved. - Image parts accept only
typeandimage_url.url; omitdetail,cache_control, and other image extensions. - Responses preserve the requested canonical model ID.
- MiMo API on RunAPI: https://runapi.ai/models/mimo
- Provider page: https://runapi.ai/providers/xiaomi
- Browse the catalog: https://runapi.ai/models
- Keep API keys in environment variables or a secret manager.
- Use streaming for long responses.
- Link to https://runapi.ai/models/mimo for pricing instead of copying values.
Licensed under the Apache License, Version 2.0.