MiniMax-H3 vs MiniMax-M3.1-Flash
| MiniMax-H3 | MiniMax-M3.1-Flash | |
|---|---|---|
| Providers | MiniMax | MiniMax |
| Input $/M | $0.0000 | $0.15 |
| Output $/M | $0.0000 | $0.62 |
| Output multiplier | ×1.00 | ×4.00 |
| Context window | — | 1M tokens |
| Intelligence index | — | — |
| Coding index | — | — |
What the numbers mean
Tags: MiniMax-H3 — Video generation · MiniMax-M3.1-Flash — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# MiniMax-H3
client.chat.completions.create(model="MiniMax-H3", messages=[{"role":"user","content":"Hi"}])
# MiniMax-M3.1-Flash
client.chat.completions.create(model="MiniMax-M3.1-Flash", messages=[{"role": "user", "content": "Hi"}])