mimolisted
Install: claude install-skill runapi-ai/mimo
# MiMo on RunAPI
Use OpenAI-compatible Chat Completions at `https://runapi.ai/v1` as the primary
protocol. Keep the exact public model identity throughout the request.
## Primary protocol recipe
### Authenticate
Set `OPENAI_API_KEY` to a RunAPI API key and `OPENAI_BASE_URL` to
`https://runapi.ai/v1`. Keep the key in the environment or a secret manager.
### Send request
```python
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": "Summarize this decision."}],
)
print(response.choices[0].message.content)
```
For longer output, request terminal usage while streaming:
```python
stream = client.chat.completions.create(
model="mimo-v2.5",
messages=[{"role": "user", "content": "Write a status update."}],
stream=True,
stream_options={"include_usage": True},
)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta.content:
print(chunk.choices[0].delta.content, end="", flush=True)
if chunk.usage:
print(chunk.usage)
```
### Verify result
For a synchronous call, require one response choice with a final assistant
message and read `usage` from that response. For SSE, consume through `[DONE]`
and require the terminal usage chunk requested by `include_usage`. An HTTP 2xx
without the expected final content and Usage is incomplete.
### Stop boundaries
Correct a rejected