MiniMax-M2 vs MiniMax-M3.1-Flash-Preview
| MiniMax-M2 | MiniMax-M3.1-Flash-Preview | |
|---|---|---|
| Providers | MiniMax | MiniMax |
| Input $/M | $0.16 | $0.07 |
| Output $/M | $0.65 | $0.30 |
| Output multiplier | ×4.00 | ×4.00 |
| Context window | 200K tokens | 1M tokens |
| Intelligence index | 18.6 | — |
| Coding index | — | — |
What the numbers mean
MiniMax-M3.1-Flash-Preview is roughly 2.2× cheaper on input than MiniMax-M2. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to MiniMax-M2 deliberately rather than by default.
Tags: MiniMax-M2 — Chat, Reasoning, Coding · MiniMax-M3.1-Flash-Preview — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# MiniMax-M2
client.chat.completions.create(model="MiniMax-M2", messages=[{"role":"user","content":"Hi"}])
# MiniMax-M3.1-Flash-Preview
client.chat.completions.create(model="MiniMax-M3.1-Flash-Preview", messages=[{"role": "user", "content": "Hi"}])