All modelsCalculate what your real prompts cost on DeepSeek V4 Flash 0423
DeepSeek V4 Flash 0423
open sourceDeepSeek model, released 24 Apr 2026.
$0.0826
per 1M input tokens
$0.165
per 1M output tokens
$0.0165
per 1M cached-read tokens
Price history
input $/1M output $/1M7 Jul 2026 → 21 Aug 2026
Specifications
- Lab
- DeepSeek
- Released
- 24 Apr 2026
- Context window
- 1.0M tokens
- Max output
- 384k tokens
- Input modalities
- text
- Output modalities
- text
- Knowledge cutoff
- —
- Open source
- Yes
Benchmarks
| Benchmark | Category | Score | As of |
|---|---|---|---|
| LMArena (Chatbot Arena) | coding | 1455.6 (1449.3–1462) | 12 Aug 2026 |
| LMArena (Chatbot Arena) | overall | 1431.5 (1427.3–1435.6) | 12 Aug 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 $0.0826 per 1M input tokens and $0.165 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 384k output tokens.