longcat-2.0 vs longcat-2.5-preview
| longcat-2.0 | longcat-2.5-preview | |
|---|---|---|
| Providers | Meituan | Meituan |
| Input $/M | $0.77 | $0.77 |
| Output $/M | $3.08 | $3.08 |
| Output multiplier | ×4.00 | ×4.00 |
| Context window | 1M tokens | 1M tokens |
| Intelligence index | 19.1 | — |
| Coding index | 45.3 | — |
What the numbers mean
Input pricing is close — 1.00× apart — so the decision should come down to measured quality on your own evaluation set rather than headline cost.
Tags: longcat-2.0 — Chat, Reasoning, Coding · longcat-2.5-preview — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# longcat-2.0
client.chat.completions.create(model="longcat-2.0", messages=[{"role":"user","content":"Hi"}])
# longcat-2.5-preview
client.chat.completions.create(model="longcat-2.5-preview", messages=[{"role": "user", "content": "Hi"}])