Model

DeepSeek V4 Flash 0423

Name: DeepSeek V4 Flash 0423
Brand: deepseek

Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads

3 providers · 3 listingsreleased Apr 23, 2026knowledge cutoff 2025-05open weights

$0.138

lowest input /M · Venice AI

$0.275

lowest output /M · Venice AI

context window

384K

max output

Compare providers (sorted by listed input price)

3 providers list DeepSeek V4 Flash 0423. The cheapest full-context option is Venice AI at $0.138/$0.275 per M. Listed prices span 1.6× for identical weights.

			Cache read /M	Cache write /M		Capabilities
Venice AI deepseek-v4-flash	$0.138	$0.275	$0.028	—	1M	reasoningtoolsstructuredno vision	Jun 11, 2026
Merge Gateway deepseek/deepseek-v4-flash-0423	$0.139	$0.278	—	—	131K	reasoningno toolsno structuredno vision	Apr 23, 2026
Ofox deepseek/deepseek-v4-flash-0423	$0.19	$0.51	$0.028	—	1M	reasoningtoolsstructuredno vision	Apr 23, 2026

Best price history

Daily lowest published price across live providers. A lower line is better for the buyer.

Best input /M: $0.138unchanged
Best output /M: $0.275unchanged
Provider coverage: 3; 3 at the start · 3 snapshots

Published best prices are unchanged.

3 daily snapshots collected from Sep 11, 2026 through Sep 14, 2026. A price chart will appear after the first real move.

Price badge

![DeepSeek V4 Flash 0423 price](https://www.vaanalytics.in/badge/deepseek/deepseek-v4-flash-0423.svg)

https://www.vaanalytics.in/badge/deepseek/deepseek-v4-flash-0423.svg

Live SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.

Recent changes

Changelog →

repricedvia ofox · Sep 13, 2026
- input: $0.44 → $0.19
- output: $1.32 → $0.51
- cache_read: $0.014 → $0.028
new modelvia ofox · Sep 11, 2026
new modelvia merge-gateway · Sep 11, 2026

Weights

Hugging Face

Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.