CheapestCoding Long-contextBest value Get an API key
🎯 Don't want to pick? Send model: "appmo/auto" and Appmo routes each request to the cheapest model that's good enough — cutting your bill up to 40%. See how →
Models › ~deepseek › DeepSeek V4 Flash Latest

DeepSeek V4 Flash Latest — pricing & benchmarks

By ~deepseek · Updated 2026-07-24 · long-context / RAGcheap high-volumestep-by-step reasoning

DeepSeek V4 Flash Latest costs $0.03 per 1M input tokens and $0.16 per 1M output tokens, with a 1M context window. It is best suited for long-context / RAG, cheap high-volume, step-by-step reasoning, and is available through one OpenAI-compatible Appmo API key.
$0.03Input / 1M
$0.16Output / 1M
1MContext
—Intelligence
—Coding
—GPQA %
—Speed tok/s

What DeepSeek V4 Flash Latest is used for

DeepSeek V4 Flash Latest is best suited for long-context / RAG, cheap high-volume, step-by-step reasoning. Access it through one Appmo API key alongside 390 other models — Appmo's optimizer can route to it automatically when it is the best value for a request.

Use it via the Appmo API (OpenAI-compatible)

curl https://appmo.com/v1/chat/completions \
  -H "Authorization: Bearer $APPMO_KEY" \
  -d '{"model":"~deepseek/deepseek-v4-flash-latest","messages":[{"role":"user","content":"Hello"}]}'

FAQ

How much does DeepSeek V4 Flash Latest cost?
DeepSeek V4 Flash Latest costs $0.03 per 1M input tokens and $0.16 per 1M output tokens ($0.063 blended), as of 2026-07-24. Prices are expected to fall as competition increases.

What is DeepSeek V4 Flash Latest best for?
DeepSeek V4 Flash Latest is best suited for long-context / RAG, cheap high-volume, step-by-step reasoning.

How do I use DeepSeek V4 Flash Latest?
Send requests to Appmo's OpenAI-compatible endpoint with model id "~deepseek/deepseek-v4-flash-latest" and one API key — no separate provider account needed.