mimo-v2.5-pro vs mimo-v2.6-flash
| mimo-v2.5-pro | mimo-v2.6-flash | |
|---|---|---|
| Providers | Xiaomi MiMo | Xiaomi MiMo |
| Input $/M | $0.23 | $0.08 |
| Output $/M | $0.46 | $0.15 |
| Output multiplier | ×2.00 | ×2.00 |
| Context window | 1M tokens | 1M tokens |
| Intelligence index | 26.0 | 37.9 |
| Coding index | 60.2 | — |
What the numbers mean
mimo-v2.6-flash is roughly 3.0× cheaper on input than mimo-v2.5-pro. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to mimo-v2.5-pro deliberately rather than by default.
On measured intelligence index the gap is 11.9 points, with mimo-v2.6-flash ahead. That is a large enough spread to be visible on multi-step tasks.
Tags: mimo-v2.5-pro — Chat, Reasoning, Coding · mimo-v2.6-flash — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# mimo-v2.5-pro
client.chat.completions.create(model="mimo-v2.5-pro", messages=[{"role":"user","content":"Hi"}])
# mimo-v2.6-flash
client.chat.completions.create(model="mimo-v2.6-flash", messages=[{"role": "user", "content": "Hi"}])