opendunes

DeepSeek V4 Flash 0423

by DeepSeekReleased 24 April 2026

DeepSeek V4 Flash is the first V4 release of the Flash size, built for fast answers over very long text. It reads about a thousand pages at once, thinks before answering when asked, uses your connected tools and fills in the exact form or table you give it. Pick it to run an agent or summarise a whole codebase quickly. DeepSeek V4 Flash 0731 is the retrained revision for coding and agents; V4 Pro is the larger model.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

You pay for what each request uses. No subscription, no minimum.

≈ 0,061 DA per message3 000 DA buys about 49 000 messages

35 % offGMICloud has cut its price. Every figure here is the new one.

One message, the ordinary use

1 000 tokens sent× 30,29 DA per 1M0,030 DA
500 tokens back× 60,58 DA per 1M0,030 DA
Total≈ 0,061 DA

Every rate

Meter↑ you send↓ comes back
Text tokens30,29 DA60,58 DA
Cached tokens read6,06 DA

per 1M tokens

Answer a quick question≈ 0,020 DA
Reply to a customer email≈ 0,042 DA
Write a one-page draft≈ 0,064 DA
Translate a full page of text≈ 0,070 DA
Explain a stack trace and suggest a fix≈ 0,082 DA
When you pay
After the answer, from your balance. Nothing is held.
Why it varies
A longer question or a longer answer costs more.
After each one
The exact charge shows on the request.
DepositDeposits from 50 DA, with Edahabia or CIB.

Where your request runs

14 companies run this model. OpenDunes sends each request to one of them, picked by price and speed. If it fails, the next one takes it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

Relace…
↑ Sent, per 1M
13,75 DA
↓ Back, per 1M
149,78 DA
Cache read
13,75 DA
Latency
…
Throughput
…
StreamLake69 % off…
↑ Sent, per 1M
Was 46,5914,49 DA
↓ Back, per 1M
Was 93,1828,98 DA
Cache read
Was 9,322,90 DA
Latency
…
Throughput
…
Baidu68 % off…
↑ Sent, per 1M
Was 46,5814,72 DA
↓ Back, per 1M
Was 93,2029,45 DA
Cache read
Was 9,302,94 DA
Latency
…
Throughput
…
DeepInfraUnited States…
↑ Sent, per 1M
29,96 DA
↓ Back, per 1M
59,91 DA
Cache read
5,99 DA
Latency
…
Throughput
…
GMICloud35 % offUnited States…
↑ Sent, per 1M
Was 46,6030,29 DA
↓ Back, per 1M
Was 93,2060,58 DA
Cache read
Was 9,326,06 DA
Latency
…
Throughput
…
Venice30 % offUnited States…
↑ Sent, per 1M
Was 45,9332,15 DA
↓ Back, per 1M
Was 91,5364,07 DA
Cache read
Was 9,316,52 DA
Latency
…
Throughput
…
DigitalOcean…
↑ Sent, per 1M
32,62 DA
↓ Back, per 1M
65,24 DA
Cache read
6,52 DA
Latency
…
Throughput
…
Fireworks…
↑ Sent, per 1M
34,95 DA
↓ Back, per 1M
69,90 DA
Cache read
6,99 DA
Latency
…
Throughput
…
SiliconFlowUnited States…
↑ Sent, per 1M
43,27 DA
↓ Back, per 1M
93,19 DA
Cache read
9,32 DA
Latency
…
Throughput
…
AtlasCloud…
↑ Sent, per 1M
46,60 DA
↓ Back, per 1M
93,19 DA
Cache read
9,32 DA
Latency
…
Throughput
…
Parasail…
↑ Sent, per 1M
46,60 DA
↓ Back, per 1M
93,19 DA
Cache read
23,30 DA
Latency
…
Throughput
…
Mancer 2…
↑ Sent, per 1M
58,25 DA
↓ Back, per 1M
166,42 DA
Cache read
58,25 DA
Latency
…
Throughput
…
AzureUnited States…
↑ Sent, per 1M
69,90 DA
↓ Back, per 1M
186,39 DA
Cache read
10,32 DA
Latency
…
Throughput
…
Wafer…
↑ Sent, per 1M
199,70 DA
↓ Back, per 1M
56,58 DA
Cache read
66,57 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Relace13,75 DA149,78 DA13,75 DA………
StreamLake69 % offWas 46,5914,49 DAWas 93,1828,98 DAWas 9,322,90 DA………
Baidu68 % offWas 46,5814,72 DAWas 93,2029,45 DAWas 9,302,94 DA………
DeepInfraUnited States29,96 DA59,91 DA5,99 DA………
GMICloud35 % offUnited StatesWas 46,6030,29 DAWas 93,2060,58 DAWas 9,326,06 DA………
Venice30 % offUnited StatesWas 45,9332,15 DAWas 91,5364,07 DAWas 9,316,52 DA………
DigitalOcean32,62 DA65,24 DA6,52 DA………
Fireworks34,95 DA69,90 DA6,99 DA………
SiliconFlowUnited States43,27 DA93,19 DA9,32 DA………
AtlasCloud46,60 DA93,19 DA9,32 DA………
Parasail46,60 DA93,19 DA23,30 DA………
Mancer 258,25 DA166,42 DA58,25 DA………
AzureUnited States69,90 DA186,39 DA10,32 DA………
Wafer199,70 DA56,58 DA66,57 DA………

You pay the price of the provider that served your request. Prices read 15:19 · speed over the last 30 minutes · uptime over 3 days.

See it in action

Real requests, real replies. Try any of them yourself — one click, pre-filled.

Structured output
You send

Turn this customer email into JSON with intent, urgency and order_id.

customer-email.txt
It replied

{ "intent": "refund", "urgency": "high", "order_id": "OD-58421" }

Try in Chat Lab
Writing
You send

Two lines to welcome a shop in Oran.

It replied

Welcome to our new shop in Oran — fresh bread every morning, and coffee the way the city likes it. Come in, the first cup is on us.

Try in Chat Lab

Try your own request — same model, pre-selected.

Open Chat Lab

Call it in code

Swap the base URL and the key. Your OpenAI code runs unchanged.

POST /v1/chat/completions
Base URL
https://opendunes.com/v1
Model ID
deepseek/deepseek-v4-flash
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://opendunes.com/v1",
    api_key=os.environ["OPENDUNES_API_KEY"],
)

resp = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)
pip install openaiFull reference for this route
Sign in to run it

Runs this request once on your balance.

Parameters you can send

Standard OpenAI fields, grouped by what they control. Anything not listed is accepted and ignored.

Shaping the reply

How long, how varied, where to stop.

max_tokenstemperaturetop_ptop_kmin_ptop_astopseedfrequency_penaltypresence_penaltyrepetition_penaltylogit_biaslogprobstop_logprobs

Reasoning

Let it think before answering — and see the thinking.

reasoningreasoning_effortinclude_reasoning

Structured output

Get JSON you can parse instead of prose.

response_formatstructured_outputs

Tools

Let the model call your functions.

toolstool_choice

Other

Also accepted by this model.

max_completion_tokens

Questions about DeepSeek V4 Flash 0423

  • How much does DeepSeek V4 Flash 0423 cost in dinars?

    About 0,061 DA per message. Was 0,094 DA. ↑ 30,29 DA · ↓ 60,58 DA per 1M tokens.

  • Is DeepSeek V4 Flash 0423 free? Can I try it?

    No. You pay per use from your balance, with no subscription. Try it in Chat at the same price.

  • What is DeepSeek V4 Flash 0423 best for?

    DeepSeek V4 Flash is the first V4 release of the Flash size, built for fast answers over very long text. It reads about a thousand pages at once, thinks before answering when asked, uses your connected tools and fills in the exact form or table you give it. Pick it to run an agent or summarise a whole codebase quickly. DeepSeek V4 Flash 0731 is the retrained revision for coding and agents; V4 Pro is the larger model.

  • DeepSeek V4 Flash 0423 or DeepSeek V4 Flash Vision Exp?

    DeepSeek V4 Flash Vision Exp costs 0,31 DA more for the same message.

  • How do I pay for DeepSeek V4 Flash 0423 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, DeepSeek V4 Flash 0423 included, is paid from that balance. No foreign card, no conversion.

  • Does DeepSeek V4 Flash 0423 work in Arabic, French or Darja?

    DeepSeek names no languages for DeepSeek V4 Flash 0423. Arabic, French and Darja: not stated.

  • Can it read PDFs, images or a whole book?

    It reads text. Up to 1M tokens in one request, about 1 000 pages. It writes up to 708 000 words at once.

  • Is DeepSeek V4 Flash 0423 open source?

    Yes, its weights are public. Open weights on Hugging Face

  • Who makes DeepSeek V4 Flash 0423, and when was it released?

    DeepSeek. Released 24 April 2026.

Other DeepSeek models, priced in dinars

See all DeepSeek models
DeepSeek V4.1 Flash 1017DeepSeek · Oct 17, 2026

#10 for 3D scenes · This is the 17 October 2026 snapshot of V4.1 Flash, the image-and-text model DeepSeek serves under its current Flash name. It keeps about a thousand pages in mind, replies up to about 393 pages, thinks first, uses your connected tools and fills in the exact form you give it. Pick it for agents and coding work that include screenshots, and when you want the newest Flash. The earlier DeepSeek V4.1 Flash is the snapshot before this one; V4 Pro 0813 is the larger model for hard reasoning.

Thinks firstUses your tools1 000 pages at once
≈0,15 DAper message
View model
DeepSeek V4.1 FlashDeepSeek · Sep 10, 2026

DeepSeek V4.1 Flash is the first DeepSeek model built on a new design, and it reads images as well as text, keeping about a thousand pages in mind. It thinks before answering, uses your connected tools and fills in the exact form you give it. Use it as the fast, everyday model for coding agents that also need to look at screenshots or diagrams.

Thinks firstUses your tools1 000 pages at once
≈0,11 DAper message
View model
DeepSeek V4 Flash 0731DeepSeek · Jul 31, 2026

DeepSeek's generally available V4 Flash, re-post-trained for coding, reasoning and agent work on the same 284B mixture-of-experts with 13B active, with tools, structured output and switchable reasoning

#27 of 119 for codingThinks firstUses your tools
≈0,070 DAper message
View model
DeepSeek V4 Pro 0813DeepSeek · Aug 12, 2026

DeepSeek V4 Pro 0813 is the general-availability release of V4 Pro, the large model for hard reasoning, coding and long agent runs. It reads about a thousand pages of text, replies up to about 384 pages, uses your connected tools and fills in the exact form you give it, with three thinking levels (low, high and max) so you choose how much it reasons.

#28 of 119 for codingThinks firstUses your tools
≈0,81 DAper message
View model