Deepseek V4.1 Flash

silvamux/deepseek-v4.1-flash
Supported modalities
text
Input price$0.3 / 1M tokensper 1M tokens
Output price$1.2 / 1M tokensper 1M tokens

Pricing

Tune and Pro share the same prices.

Input contextInputOutputCache readCache write
-$0.3 / 1M tokens$1.2 / 1M tokens$0.006 / 1M tokens$0.3 / 1M tokens

Capabilities

Evaluation data not available yet

Performance

Deepseek V4.1 Flash Tune

deepseek-v4.1-flash@tune
Last 24 hours · 141,979 requests
First token · TTFT · P50
1246ms
P95 2112 ms
Output speed · TPS · P50
44tok/s
P95 60 tok/s
Full response · E2E · P50
8.35s
P95 9.35 s
Request success rate
97.33%
138,193 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://silvamux.io/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"}]
  }'