whichllmmodel
Back to Dashboard
💬 Text ModelOpen Source

DeepSeek V4 Flash

by DeepSeek

✍️ Analysis by:the whichllmmodel Editorial Team|📅 Updated: June 2026
API Reference

Benchmark Evaluations

Codingswe-bench-pro

49.1%

Reasoninggpqa-diamond

80%

Pricing & Speed Details

Input Cost

$0.14

per 1M tokens
Output Cost

$0.28

per 1M tokens
Blended Cost

$0.17

based on 3:1 ratio
Speed

109.1 tps

Context Window

1M tokens

Want to test this model?

Compare DeepSeek V4 Flash dynamically against other top AI models on our comparison dashboard to optimize your choice.

Go to Dashboard

Quick Info

  • ProviderDeepSeek
  • CategoryText / Chat Generation
  • LicenseOpen Source

Frequently Asked Questions

DeepSeek V4 Flash has a blended cost of $0.17 per 1 million tokens (calculated using a standard 3:1 input-to-output token ratio). Its specific pricing is $0.14 per 1M input tokens and $0.28 per 1M output tokens.

DeepSeek V4 Flash supports a context window of 1M tokens. This allows it to process large documents, codebase segments, or long chat histories in a single query session.

DeepSeek V4 Flash scores 49.1% on coding evaluations (SWE-bench-pro) and 80% on reasoning tasks (GPQA-diamond).

DeepSeek V4 Flash is an open source model developed by DeepSeek.