← All models
DeepSeek V4.1 Flash
deepseek/deepseek-flash
DeepSeek's newest model, with native multimodal input and thinking and non-thinking modes.
Context
1M
Input
$0.30/M
Output
$1.20/M
Released
2026-09
Peak-hour price shown; off-peak is 50% lower ($0.15 in / $0.60 out).
Price source: api-docs.deepseek.com · list price checked Oct 2026
textimageDeepSeek
Use this model
from openai import OpenAI
client = OpenAI(base_url="https://magicai.lol/v1", api_key="<MAGICAI_API_KEY>")
resp = client.chat.completions.create(
model="deepseek-flash",
messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)Performance
Latency (TTFT)
— (collecting)
Throughput
— (collecting)
Uptime
— (collecting)
Live performance stats appear once the model has traffic on MagicAI. Prices shown are catalog list prices and may differ from final gateway pricing.