deepseek

DeepSeek: DeepSeek V4 Flash 0423

The DeepSeek V4 Flash 0423 is a language model developed by deepseek that handles text input modalities up to 1 MB in context length and supports both tools and reasoning capabilities. For users looking for an affordable option with robust reasoning abilities, this model may be worth considering, particularly given its relatively low price point of $0.0886 per million input tokens. However, it is essential to note that the model's performance remains unproven due to the lack of available benchmark coverage; further evaluation would be necessary to determine its effectiveness in real-world applications.

Open weights 284B parameters, about 158.7 GiB at Q4_K_M: fits comfortably on 0 of 17 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
99/100
price + capability + benchmarks
Input Price
$0.09
per 1M tokens · checked 2026-09-07
Output Price
$0.18
per 1M tokens · checked 2026-09-07
Context Window
1,048,576
tokens
Model ID
deepseek/deepseek-v4-flash
Vendor
deepseek
Released
April 2026
Tokenizer
DeepSeek
Input Modalities
text
Output Modalities
text
Max Output
384,000 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.09/M input and $0.18/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.05
A month of a busy support chatbot 5M in / 2M out $0.80

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-09-07 $0.09 $0.18 1,048,576
2026-09-06 $0.08 $0.16 1,048,576
2026-09-05 $0.09 $0.17 1,048,576
2026-09-02 $0.09 $0.18 1,048,576
2026-09-01 $0.08 $0.15 1,048,576
2026-08-29 $0.09 $0.17 1,048,576
2026-08-28 $0.09 $0.18 1,048,576
2026-08-27 $0.08 $0.16 1,048,576
2026-08-25 $0.09 $0.18 1,048,576
2026-08-24 $0.06 $0.11 1,048,576
2026-08-23 $0.05 $0.11 1,048,576
2026-08-22 $0.08 $0.15 1,048,576
2026-08-21 $0.08 $0.17 1,048,576
2026-08-20 $0.09 $0.18 1,048,576
2026-08-18 $0.08 $0.17 1,048,576
2026-08-17 $0.08 $0.17 1,048,576
2026-08-16 $0.06 $0.13 1,048,576
2026-08-15 $0.08 $0.16 1,048,576
2026-08-08 $0.14 $0.28 1,048,576
2026-08-06 $0.09 $0.18 1,048,576
2026-07-26 $0.14 $0.28 1,048,576
2026-07-25 $0.09 $0.19 1,048,576
2026-07-23 $0.10 $0.20 1,048,576
2026-07-21 $0.09 $0.19 1,048,576
2026-07-17 $0.10 $0.20 1,048,576

Similar models

Quick answers

How much does DeepSeek: DeepSeek V4 Flash 0423 cost?
$0.09 per million input tokens and $0.18 per million output tokens.
What is DeepSeek: DeepSeek V4 Flash 0423's context window?
1,048,576 tokens, roughly 1,572 pages of text in a single request.
Does DeepSeek: DeepSeek V4 Flash 0423 support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can DeepSeek: DeepSeek V4 Flash 0423 process images?
No, it is text-only on the input side.