| gemini-3.6-flash | MiniMax-M3 | |
|---|---|---|
| Providers | — | — |
| Input $/M | $1.50 | $0.64 |
| Output $/M | $7.50 | $2.55 |
| Output multiplier | ×5.00 | ×4.00 |
| Context window | — | — |
| Intelligence index | 40.3 | 35.7 |
| Coding index | 69.2 | 58.6 |
MiniMax-M3 is roughly 2.4× cheaper on input than gemini-3.6-flash. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to gemini-3.6-flash deliberately rather than by default.
On measured intelligence index the gap is 4.6 points, with gemini-3.6-flash ahead. That is a large enough spread to be visible on multi-step tasks.
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# gemini-3.6-flash
client.chat.completions.create(model="gemini-3.6-flash", messages=[{"role":"user","content":"Hi"}])
# MiniMax-M3
client.chat.completions.create(model="MiniMax-M3", messages=[{"role": "user", "content": "Hi"}])