Configure OpenAI-compatible clients to use MiniMax text models on RunAPI.
Model Reference | Skill Repo | All Models
Call MiniMax text models through RunAPI with the official OpenAI SDK or any
OpenAI-compatible client. Point clients at https://runapi.ai/v1, send
MiniMax-M3, MiniMax-M2.7, MiniMax-M2.7-highspeed, MiniMax-M2.5,
MiniMax-M2.5-highspeed, MiniMax-M2.1, or MiniMax-M2, and pay through one
RunAPI balance. This skill teaches Claude Code, Codex, Gemini CLI, Cursor, and
50+ agents how to wire MiniMax text requests through RunAPI.
The canonical agent file is skills/minimax/SKILL.md.
npx skills add runapi-ai/minimax -gOr paste this prompt to your AI agent:
Install the minimax skill for me:
1. Clone https://github.com/runapi-ai/minimax
2. Copy the skills/minimax/ 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="MiniMax-M3",
messages=[{"role": "user", "content": "Hello, MiniMax!"}],
)
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.chat.completions.create({
model: "MiniMax-M2.7-highspeed",
messages: [{ role: "user", content: "Hello, MiniMax!" }],
});
console.log(response.choices[0].message.content);Get a RunAPI API Key at https://runapi.ai/api_keys.
| Model ID | Notes |
|---|---|
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 |
- MiniMax API on RunAPI: https://runapi.ai/models/minimax
- Provider page: https://runapi.ai/providers/minimax
- Browse the full RunAPI catalog: https://runapi.ai/models
- Skill repository: https://github.com/runapi-ai/minimax
- Keep API keys in
OPENAI_API_KEYor your secret manager; never inline them in commits or shell history. - Stream long responses (
stream: true) so the agent can release the terminal/IO loop early. - This skill is for MiniMax text models. Use the Hailuo skill for video.
- For pricing, rate-limit, and commercial-usage answers, link to https://runapi.ai/models/minimax rather than this README.
Licensed under the Apache License, Version 2.0.