Deepseek V4.1 Flash

silvamux/deepseek-v4.1-flash
Input price¥2 / 1M tokensper 1M tokens
Output price¥8 / 1M tokensper 1M tokens
Context1M
Max output356K

Pricing

Tune and Pro share the same prices.

Input contextInputOutputCache readCache write
-¥2 / 1M tokens¥8 / 1M tokens¥0.04 / 1M tokens¥2 / 1M tokens

Capabilities

Evaluation data not available yet

Performance

Deepseek V4.1 Flash Tune

deepseek-v4.1-flash@tune
Last 24 hours · 52,776 requests
First token · TTFT · P50
1646ms
P95 1794 ms
Output speed · TPS · P50
46tok/s
P95 69 tok/s
Full response · E2E · P50
7.25s
P95 9.94 s
Request success rate
98.54%
52,006 completed requests
24-hour availability
24 hours ago12 hours agoNow

Deepseek V4.1 Flash example code and API

Tunedeepseek-v4.1-flash@tune
/api/v0/chat/completions/api/v1/chat/completions
UnifiedOpenAI
curl https://www.silvamux.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4.1-flash@tune",
    "messages": [{"role": "user", "content": "Hello, please introduce yourself"}]
  }'