MiniMax on RunAPI
Use OpenAI-compatible Chat Completions at https://runapi.ai/v1 as the primary protocol. Use the separate Hailuo skill for video generation.
Primary protocol recipe
Authenticate
Set OPENAI_API_KEY to a RunAPI API key and OPENAI_BASE_URL to https://runapi.ai/v1.
Send request
from openai import OpenAI
client = OpenAI(api_key="YOUR_RUNAPI_TOKEN", base_url="https://runapi.ai/v1")
response = client.chat.completions.create(
model="MiniMax-M3",
messages=[{"role": "user", "content": "Draft a support response."}],
)
print(response.choices[0].message.content)
print(response.usage)
For long output, set stream=True and
stream_options={"include_usage": True}; consume through [DONE].
Verify result
Require final assistant content, finish_reason, and authoritative usage.
A stream is complete only after its terminal usage chunk and [DONE].
Stop boundaries
Correct a rejected shape once using the structured error. Retry transport once only before any response or Usage and when replay is safe. Record a terminal error and stop without changing model or protocol.
Compatibility protocols
Load compatibility protocols only when an existing client requires Anthropic Messages or Gemini contents.
Supported models
| Model ID | Use when |
|---|---|
MiniMax-M3 |
Latest MiniMax text chat |
MiniMax-M2.7 |
MiniMax M2.7 compatibility |
MiniMax-M2.7-highspeed |
Faster MiniMax M2.7 requests |
MiniMax-M2.5 |
MiniMax M2.5 compatibility |
MiniMax-M2.5-highspeed |
Faster MiniMax M2.5 requests |
MiniMax-M2.1 |
MiniMax M2.1 compatibility |
MiniMax-M2 |
MiniMax M2 compatibility |