All models

DeepSeek V4 Flash 0423

open source

DeepSeek model, released 24 Apr 2026.

$0.0224
per 1M input tokens
$1.28
per 1M output tokens
$0.0224
per 1M cached-read tokens
Calculate what your real prompts cost on DeepSeek V4 Flash 0423

Price history

input $/1M output $/1M7 Jul 2026 → 4 Oct 2026

Specifications

Lab
DeepSeek
Released
24 Apr 2026
Context window
1.0M tokens
Max output
944k tokens
Input modalities
text
Output modalities
text
Knowledge cutoff
—
Open source
Yes

Benchmarks

BenchmarkCategoryScoreAs of
LMArena (Chatbot Arena)coding1455.6 (1449.3–1461.9)13 Sept 2026
LMArena (Chatbot Arena)overall1431.8 (1427.7–1435.9)13 Sept 2026

LMArena (Chatbot Arena) data © their authors, CC-BY-4.0

Frequently asked questions

How much does DeepSeek V4 Flash 0423 cost?

DeepSeek V4 Flash 0423 costs $0.0224 per 1M input tokens and $1.28 per 1M output tokens (list price, updated every 6 hours).

What is DeepSeek V4 Flash 0423's context window?

DeepSeek V4 Flash 0423 supports a 1.0M-token context window with up to 944k output tokens.

Related models