DeepSeek V4 Flash

deepseek/deepseek-v4-flash-20260423

DeepSeek V4 Flash, released by DeepSeek on 2026‑04‑24, processes text input and generates text output. The model supports tools, reasoning, a context length of 1,048,576 tokens, and its weights are not open. Pricing is $0.0938 per M input tokens and $0.1876 per M output tokens.

  • tool use
  • structured outputs
  • reasoning

At a glance

providerdeepseek
releasedApr 24, 2026
context1.0M
input / M$0.094

Specifications

What the API gives you

Context window
1.0M tokens
Max output
Input price
$0.094 / 1M tokens
Output price
$0.19 / 1M tokens
Cache read
$0.019 / 1M tokens
Modalities
text → text
Knowledge cutoff
Released
Apr 24, 2026

Recommendation coverage

Where this model appears

  1. #4Best LLM for RAG & Long Context

Measured evidence

Public benchmark record

LMArena Agent
-4.62026-07-13
LMArena Agent
-3.82026-07-20
LMArena Text
1433 Elo2026-07-16

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open.

Open-weight model on Hugging Face.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.