DeepSeek

DeepSeek-V4-Flash

azure/deepseek-v4-flash

  • Input: text
  • Output: text

RuntimeWire coverage

  • DwarfStar compresses frontier models to run them on local machines
  • DeepSeek publishes 168GB vision model weights under an MIT license
  • Head to head: Google: Gemini 3.7 Flash vs DeepSeek-V4-Flash
  • Open-weight models surge past closed rivals in Vercel token traffic
  • CTGT says DeepSeek distillation lifted finance scores without censorship transfer

View on OpenRouter. Model data sourced from OpenRouter.