| deepseek-flash | MiniMax-M2 | |
|---|---|---|
| Providers | — | — |
| Input $/M | $0.15 | $0.32 |
| Output $/M | $0.61 | $1.27 |
| Output multiplier | ×4.00 | ×4.00 |
| Context window | — | — |
| Intelligence index | — | — |
| Coding index | — | — |
deepseek-flash is roughly 2.1× 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.
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# deepseek-flash
client.chat.completions.create(model="deepseek-flash", messages=[{"role":"user","content":"Hi"}])
# MiniMax-M2
client.chat.completions.create(model="MiniMax-M2", messages=[{"role": "user", "content": "Hi"}])