opendunes

DeepSeek V4.1 Flash 1017 (batch)

by DeepSeekReleased 17 October 2026

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.

TakesTextImages
GivesText

Where your request runs

Three companies run this model. OpenDunes sends each request to one of them. DA per 1M tokens: ↑ what you send · ↓ what comes back.

MorphUnited States…
↑ Sent, per 1M
11,98 DA
↓ Back, per 1M
49,93 DA
Cache read
1,00 DA
Latency
…
Throughput
…
Sail Research…
↑ Sent, per 1M
16,64 DA
↓ Back, per 1M
49,93 DA
Cache read
1,33 DA
Latency
…
Throughput
…
Together…
↑ Sent, per 1M
49,93 DA
↓ Back, per 1M
199,70 DA
Cache read
1,00 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
MorphUnited States11,98 DA49,93 DA1,00 DA………
Sail Research16,64 DA49,93 DA1,33 DA………
Together49,93 DA199,70 DA1,00 DA………

You pay the price of the provider that served your request. Prices read 02:48 · speed over the last 30 minutes · uptime over 3 days.

What it costs

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

≈ 0,037 DA per message3 000 DA buys about 81 000 messages

One message, the ordinary use

1 000 sent1 000 tokens sent× 11,98 per 1M× 11,98 DA per 1M0,012 DA
500 back500 tokens back× 49,93 per 1M× 49,93 DA per 1M0,025 DA
Total≈ 0,037 DA

Every rate

Meter↑ you send↓ comes back
Text tokens11,98 DA49,93 DA
Cached tokens read1,00 DA

per 1M tokens

Everyday jobs, priced

Reasoned review of a long contract with tool calls to check clauses against your policy notes≈ 2,19 DA
Daily re-asking of the same large prompt with only the date and figures changed, billed at the cached rate≈ 6,09 DA
Summarise a full code repository with images and docs included, answered in one pass≈ 11,18 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.
Add creditDeposits from 100 DA, withEdahabiaCIB

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-v4.1-flash-1017:batch
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-v4.1-flash-1017:batch",
    messages=[{"role": "user", "content": "Two lines to welcome a shop in Oran."}],
)

print(resp.choices[0].message.content)

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

Limits

The hard numbers — what it can take in, what it can give back, and where it stops.

Context window
1 048 576 tokens
Max output
943 718 tokens
Reads at once
≈ 1 000 pages
Longest reply
≈ 708 000 words
Tokenizer
DeepSeek
Released
17 Oct 2026
Full API reference

Questions about DeepSeek V4.1 Flash 1017 (batch)

How much does DeepSeek V4.1 Flash 1017 (batch) cost in dinars?

About 0,037 DA per message. ↑ 11,98 DA · ↓ 49,93 DA per 1M tokens.

Is DeepSeek V4.1 Flash 1017 (batch) free? Can I try it?

No. You pay per use from your balance in dinars, with no subscription. The chat has free models for free messages every day.

What is DeepSeek V4.1 Flash 1017 (batch) best for?

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.

How do I pay for DeepSeek V4.1 Flash 1017 (batch) without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, DeepSeek V4.1 Flash 1017 (batch) included, is paid from that balance. No foreign card, no conversion.

Does DeepSeek V4.1 Flash 1017 (batch) work in Arabic, French or Darja?

DeepSeek names no languages for DeepSeek V4.1 Flash 1017 (batch). Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

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

Is DeepSeek V4.1 Flash 1017 (batch) open source?

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

Who makes DeepSeek V4.1 Flash 1017 (batch), and when was it released?

DeepSeek. Released 17 October 2026.

Other DeepSeek models, priced in dinars

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

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
≈0,095 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
≈0,12 DAper message
View model
DeepSeek V4 Flash 0731DeepSeek · Jul 31, 2026

This July 2026 revision of V4 Flash was trained further to suit coding, reasoning and agent work. It keeps the same size, reads about a thousand pages of text, can think first, uses your connected tools and fills in the exact form you give it.

#27 of 118 for codingThinks firstUses your tools
≈0,050 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
≈0,060 DAper message
View model