Back to Models

DeepSeek V4 Flash

FeaturedActive
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

Context Length1000K tokens
Max Output384K tokens
Lowest Input Price$0.20/1M tokens
Lowest Output Price$0.59/1M tokens

Capabilities

chatcodefunction_calling

Pricing

Input$0.20/1M
Output$0.59/1M
Cached$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