DeepSeek V4 Flash — a latency-optimized DeepSeek V4 variant for high-volume, low-cost inference.

Sampling temperature. Lower is more deterministic.
USD estimate $0.0005-$0.001: highest recharge package uses $1 = 2,000 credits; entry package uses $1 = 1,000 credits.

History
Saved locally in this browser
0 running · 0 completed
Input
≈ $0.00006-$0.0001
Output
≈ $0.0001-$0.0003
Cache
≈ $0.00001-$0.00002
Context
Max output
API
curl /v1/chat/completions \
-H "Authorization: Bearer sk-your-api-key" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4-flash",
"messages": [
{
"role": "user",
"content": "Summarize the following text in three concise bullet points:"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'