DeepSeek-V4-Flash

DeepSeek-V4-Flash (DeepSeek) — 128K context, Lightweight tier. Input price $0.14/M · Output price $0.28/M · Avg latency 18ms. Routed via Routara OpenAI-compatible endpoint with multi-region failover and metered billing.

Input / 1M: $0.14/M · Output / 1M: $0.28/M · TTFT: 18ms

Specifications

  • Developer: DeepSeek
  • Category: Lightweight
  • Context window: 128K
  • Input price: $0.14 / 1M
  • Output price: $0.28 / 1M
  • Avg latency: 18 ms
  • SLA grade: A

Typical use cases

  • High-QPS classification and routing
  • Multilingual chatbots and customer support
  • RAG pipelines with tool calling

FAQ

  • How is DeepSeek-V4-Flash priced on Routara? — Input tokens are billed at $0.14/M and output at $0.28/M. Charges are metered per request with no separate platform fee.
  • Is DeepSeek-V4-Flash OpenAI-compatible? — Yes. Point any OpenAI SDK to https://api.routara.ai/v1 and set model to the Routara slug shown below.
  • Does DeepSeek-V4-Flash support streaming? — Streaming is supported when the upstream route is live. Use stream: true in chat.completions.

Related models

  • MiniMax-File-Upload (/detail/minimax-file-upload)
  • MiniMax-Voice-Clone (/detail/minimax-voice-clone)
  • MiniMax-Hailuo-02 (/detail/minimax-hailuo-02)

Quick integration

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