deepseek-flash vs deepseek-v4-flash
| deepseek-flash | deepseek-v4-flash | |
|---|---|---|
| Providers | DeepSeek | DeepSeek |
| Input $/M | $0.15 | $0.15 |
| Output $/M | $0.62 | $0.62 |
| Output multiplier | ×4.00 | ×4.00 |
| Context window | 1M tokens | 1M tokens |
| Intelligence index | — | 34.3 |
| Coding index | — | 69.1 |
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: deepseek-flash — Chat, Reasoning, Coding, Vision · deepseek-v4-flash — Chat, Reasoning, Coding
Code
from openai import OpenAI
client = OpenAI(base_url="https://starseaapi.com/v1", api_key="sk-...")
# deepseek-flash
client.chat.completions.create(model="deepseek-flash", messages=[{"role":"user","content":"Hi"}])
# deepseek-v4-flash
client.chat.completions.create(model="deepseek-v4-flash", messages=[{"role": "user", "content": "Hi"}])