opendunes

DeepSeek V4 Pro 0813

by DeepSeekReleased 12 August 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.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

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

≈ 0,81 DA per message3 000 DA buys about 3 600 messages

One message, the ordinary use

1 000 tokens sent× 38,78 DA per 1M0,039 DA
500 tokens back× 1 551,01 DA per 1M0,78 DA
Total≈ 0,81 DA

Every rate

Meter↑ you send↓ comes back
Text tokens38,78 DA1 551,01 DA
Cached tokens read36,94 DA

per 1M tokens

Answer a quick question≈ 0,39 DA
Reply to a customer email≈ 0,64 DA
Explain a stack trace and suggest a fix≈ 0,99 DA
Translate a full page of text≈ 1,27 DA
Review a 300-line pull request≈ 1,55 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

21 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
33,25 DA
↓ Back, per 1M
2 662,68 DA
Cache read
33,25 DA
Latency
…
Throughput
…
WaferUnited States…
↑ Sent, per 1M
38,78 DA
↓ Back, per 1M
1 551,01 DA
Cache read
36,94 DA
Latency
…
Throughput
…
Wafer…
↑ Sent, per 1M
94,86 DA
↓ Back, per 1M
1 431,19 DA
Cache read
94,53 DA
Latency
…
Throughput
…
AlibabaAsia…
↑ Sent, per 1M
193,31 DA
↓ Back, per 1M
579,93 DA
Cache read
19,33 DA
Latency
…
Throughput
…
Baidu50 % off…
↑ Sent, per 1M
Was 439,34219,23 DA
↓ Back, per 1M
Was 1 318,04657,70 DA
Cache read
Was 13,996,98 DA
Latency
…
Throughput
…
AlibabaUnited States…
↑ Sent, per 1M
219,67 DA
↓ Back, per 1M
659,01 DA
Cache read
21,97 DA
Latency
…
Throughput
…
StreamLake50 % off…
↑ Sent, per 1M
Was 439,34219,67 DA
↓ Back, per 1M
Was 1 318,02659,01 DA
Cache read
Was 14,647,32 DA
Latency
…
Throughput
…
DeepSeek…
↑ Sent, per 1M
219,67 DA
↓ Back, per 1M
659,01 DA
Cache read
7,32 DA
Latency
…
Throughput
…
Phala34 % off…
↑ Sent, per 1M
Was 482,61318,52 DA
↓ Back, per 1M
Was 1 451,17957,77 DA
Cache read
Was 49,9232,95 DA
Latency
…
Throughput
…
Novita25 % off…
↑ Sent, per 1M
Was 439,35329,51 DA
↓ Back, per 1M
Was 1 318,03988,52 DA
Cache read
Was 14,6410,98 DA
Latency
…
Throughput
…
GMICloud20 % offUnited States…
↑ Sent, per 1M
Was 439,34351,47 DA
↓ Back, per 1M
Was 1 318,031 054,42 DA
Cache read
Was 14,6511,72 DA
Latency
…
Throughput
…
DeepInfraUnited States…
↑ Sent, per 1M
432,69 DA
↓ Back, per 1M
865,37 DA
Cache read
33,28 DA
Latency
…
Throughput
…
CoreWeaveUnited States…
↑ Sent, per 1M
436,01 DA
↓ Back, per 1M
1 318,03 DA
Cache read
14,64 DA
Latency
…
Throughput
…
BaseTen…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
43,93 DA
Latency
…
Throughput
…
AtlasCloud…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
43,93 DA
Latency
…
Throughput
…
Nebius…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
13,31 DA
Latency
…
Throughput
…
Parasail…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
14,64 DA
Latency
…
Throughput
…
Together…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
43,27 DA
Latency
…
Throughput
…
DigitalOcean…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
14,64 DA
Latency
…
Throughput
…
SiliconFlowUnited States…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
14,64 DA
Latency
…
Throughput
…
Cloudflare…
↑ Sent, per 1M
439,34 DA
↓ Back, per 1M
1 318,03 DA
Cache read
14,64 DA
Latency
…
Throughput
…
Sail ResearchUnited States…
↑ Sent, per 1M
449,33 DA
↓ Back, per 1M
798,81 DA
Cache read
64,90 DA
Latency
…
Throughput
…
Sail Research…
↑ Sent, per 1M
449,33 DA
↓ Back, per 1M
798,81 DA
Cache read
64,90 DA
Latency
…
Throughput
…
VeniceUnited States…
↑ Sent, per 1M
549,18 DA
↓ Back, per 1M
1 647,54 DA
Cache read
54,92 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Relace33,25 DA2 662,68 DA33,25 DA………
WaferUnited States38,78 DA1 551,01 DA36,94 DA………
Wafer94,86 DA1 431,19 DA94,53 DA………
AlibabaAsia193,31 DA579,93 DA19,33 DA………
Baidu50 % offWas 439,34219,23 DAWas 1 318,04657,70 DAWas 13,996,98 DA………
AlibabaUnited States219,67 DA659,01 DA21,97 DA………
StreamLake50 % offWas 439,34219,67 DAWas 1 318,02659,01 DAWas 14,647,32 DA………
DeepSeek219,67 DA659,01 DA7,32 DA………
Phala34 % offWas 482,61318,52 DAWas 1 451,17957,77 DAWas 49,9232,95 DA………
Novita25 % offWas 439,35329,51 DAWas 1 318,03988,52 DAWas 14,6410,98 DA………
GMICloud20 % offUnited StatesWas 439,34351,47 DAWas 1 318,031 054,42 DAWas 14,6511,72 DA………
DeepInfraUnited States432,69 DA865,37 DA33,28 DA………
CoreWeaveUnited States436,01 DA1 318,03 DA14,64 DA………
BaseTen439,34 DA1 318,03 DA43,93 DA………
AtlasCloud439,34 DA1 318,03 DA43,93 DA………
Nebius439,34 DA1 318,03 DA13,31 DA………
Parasail439,34 DA1 318,03 DA14,64 DA………
Together439,34 DA1 318,03 DA43,27 DA………
DigitalOcean439,34 DA1 318,03 DA14,64 DA………
SiliconFlowUnited States439,34 DA1 318,03 DA14,64 DA………
Cloudflare439,34 DA1 318,03 DA14,64 DA………
Sail ResearchUnited States449,33 DA798,81 DA64,90 DA………
Sail Research449,33 DA798,81 DA64,90 DA………
VeniceUnited States549,18 DA1 647,54 DA54,92 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-pro-0813
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-pro-0813",
    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_pstopseedfrequency_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

Questions about DeepSeek V4 Pro 0813

  • How much does DeepSeek V4 Pro 0813 cost in dinars?

    About 0,81 DA per message. ↑ 38,78 DA · ↓ 1 551,01 DA per 1M tokens.

  • Is DeepSeek V4 Pro 0813 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 Pro 0813 best for?

    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.

  • DeepSeek V4 Pro 0813 or DeepSeek V4 Flash Vision Exp?

    DeepSeek V4 Flash Vision Exp costs 0,44 DA less for the same message.

  • How do I pay for DeepSeek V4 Pro 0813 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, DeepSeek V4 Pro 0813 included, is paid from that balance. No foreign card, no conversion.

  • Does DeepSeek V4 Pro 0813 work in Arabic, French or Darja?

    DeepSeek names no languages for DeepSeek V4 Pro 0813. 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 Pro 0813 open source?

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

  • Who makes DeepSeek V4 Pro 0813, and when was it released?

    DeepSeek. Released 12 August 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 Flash 0423DeepSeek · Apr 24, 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.

Thinks firstUses your tools1 000 pages at once
≈0,061 DAper message
View model