StarAPI
deepseek-v3.2 vs deepseek-v4-pro
| deepseek-v3.2 | deepseek-v4-pro | |
|---|---|---|
| Providers | DeepSeek | DeepSeek |
| Input $/M | $0.30 | $0.68 |
| Output $/M | $0.45 | $2.05 |
| Output multiplier | ×1.50 | ×3.00 |
| Context window | 128K tokens | 1M tokens |
| Intelligence index | — | 42.1 |
| Coding index | 44.2 | 68.8 |
What the numbers mean
deepseek-v3.2 is roughly 2.2× cheaper on input than deepseek-v4-pro. If your workload passes the quality bar on the cheaper model, that gap compounds across every request; route to deepseek-v4-pro deliberately rather than by default.
Tags: deepseek-v3.2 — Chat, Reasoning, Coding · deepseek-v4-pro — Chat, Reasoning, Coding
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# deepseek-v3.2
client.chat.completions.create(model="deepseek-v3.2", messages=[{"role":"user","content":"Hi"}])
# deepseek-v4-pro
client.chat.completions.create(model="deepseek-v4-pro", messages=[{"role": "user", "content": "Hi"}])