DeepSeektext

DeepSeek V4 Flash

Lower-latency DeepSeek V4 variant optimized for cost-sensitive chat and structured generation at scale.

deepseek-v4-flash

Quickstart

Call this model

Chat completion

curl https://inference-api.worldrouter.ai/v1/chat/completions \
  -H "Authorization: Bearer your_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'