Meterary
Start free

DeepSeek

DeepSeek V4 Flash API Pricing

inputPerMTok is the cache-miss (standard) input rate; cachedInputPerMTok is the cache-hit rate. Non-thinking mode is the legacy alias `deepseek-chat`; thinking mode is the legacy alias `deepseek-reasoner` (both aliases scheduled for deprecation 2026-07-24, after which they route here). Concurrency limit 2,500.

Verified against DeepSeek’s pricing page on 2026-07-02.

View source ↗

Facts

Specs

  • FamilyDeepSeek V4
  • API IDdeepseek-v4-flash
  • ModalityText
  • Context window1M tokens
  • Max output384K tokens
  • Release dateNot published

Pricing (per 1M tokens)

  • Input$0.14 / 1M tokens
  • Output$0.28 / 1M tokens
  • Cached input$0.0028 / 1M tokens
  • Cache write—
  • Batch discount—

Capabilities

tool-use, reasoning, json-mode

Notes

inputPerMTok is the cache-miss (standard) input rate; cachedInputPerMTok is the cache-hit rate. Non-thinking mode is the legacy alias `deepseek-chat`; thinking mode is the legacy alias `deepseek-reasoner` (both aliases scheduled for deprecation 2026-07-24, after which they route here). Concurrency limit 2,500.

Worked cost examples

Estimated monthly cost on three common usage shapes

WorkloadEst. monthly cost

Chatbot

800 input / 200 output tokens per request, 100,000 requests/month

$16.80

RAG pipeline

6,000 input / 700 output tokens per request, 30,000 requests/month

$31.08

Batch summarization

20,000 input / 1,500 output tokens per request, 5,000 requests/month

$16.10

Price history

Changes we have documented since we began tracking

No price changes recorded since we began tracking.

DeepSeek V4 Flash pricing FAQ

How much does DeepSeek V4 Flash cost per 1M tokens?
DeepSeek V4 Flash costs $0.14 per 1M input tokens and $0.28 per 1M output tokens.
How much does DeepSeek V4 Flash cost per request?
A typical request of 800 input and 200 output tokens costs about $0.000168 on DeepSeek V4 Flash.
Is DeepSeek V4 Flash cheaper than DeepSeek V4 Pro?
DeepSeek V4 Flash is cheaper than DeepSeek V4 Pro on input tokens, by about 68%.
Does DeepSeek V4 Flash have cache pricing?
Yes — cached input reads cost $0.0028 per 1M tokens.

Keep exploring

Estimate my usage

Related models