kimi-k2.8-preview vs kimi-k3.1-pro
| kimi-k2.8-preview | kimi-k3.1-pro | |
|---|---|---|
| Providers | Moonshot AI | Moonshot AI |
| Input $/M | $1.00 | $2.00 |
| Output $/M | $4.15 | $10.46 |
| Output multiplier | ×4.15 | ×5.23 |
| Context window | 1M tokens | 256K tokens |
| Intelligence index | — | — |
| Coding index | — | — |
What the numbers mean
kimi-k2.8-preview is roughly 2.0× cheaper on input than kimi-k3.1-pro. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to kimi-k3.1-pro deliberately rather than by default.
Tags: kimi-k2.8-preview — Chat, Reasoning, Coding, Vision · kimi-k3.1-pro — Chat, Reasoning, Coding, Vision
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# kimi-k2.8-preview
client.chat.completions.create(model="kimi-k2.8-preview", messages=[{"role":"user","content":"Hi"}])
# kimi-k3.1-pro
client.chat.completions.create(model="kimi-k3.1-pro", messages=[{"role": "user", "content": "Hi"}])