Back to Models

DeepSeek V4 Flash

Nổi bậtĐang hoạt động
deepseek-v4-flash

DeepSeek V4 Flash — fast OpenAI-compatible model with automatic context caching and an optional thinking mode (reasoning tokens counted inside completion tokens).

Try in Playground

Technical Specifications

Độ dài ngữ cảnh1000K tokens
Đầu ra tối đa384K tokens
Giá đầu vào thấp nhất$0.20/1M tokens
Giá đầu ra thấp nhất$0.59/1M tokens

Capabilities

chatcodefunction_calling

Giá

Đầu vào$0.20/1M
Đầu ra$0.59/1M
Bộ nhớ đệm$0.0063/1M

Code Examples

curl https://api.tokligence.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    "max_tokens": 1024
  }'

Ready to use DeepSeek V4 Flash?

Try it out in our interactive playground or integrate it into your application with just a few lines of code.

Open PlaygroundGet API Key