opendunes

DeepSeek V3.1 Terminus

by DeepSeekReleased 22 September 2025

DeepSeek V3.1 Terminus is a maintenance release of V3.1 that fixes replies mixing languages and strengthens agents that write code and agents that search. It keeps the choice between thinking and answering directly, reads about 160 pages of text and allows replies up to about 147 pages. Use it for agents that browse, search and edit code, and for multilingual answers that must stay in one language. DeepSeek V3.2 is the next generation.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

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

≈ 0,26 DA per message3 000 DA buys about 11 000 messages

One message, the ordinary use

1 000 tokens sent× 89,87 DA per 1M0,090 DA
500 tokens back× 332,84 DA per 1M0,17 DA
Total≈ 0,26 DA

Every rate

Meter↑ you send↓ comes back
Text tokens89,87 DA332,84 DA

per 1M tokens

Answer a quick question≈ 0,097 DA
Reply to a customer email≈ 0,19 DA
Translate a full page of text≈ 0,33 DA
Explain a stack trace and suggest a fix≈ 0,33 DA
Review a 300-line pull request≈ 0,66 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

One company runs this model. OpenDunes sends every request to it. DA per 1M tokens: ↑ what you send · ↓ what comes back.

SiliconFlowUnited States…
↑ Sent, per 1M
89,87 DA
↓ Back, per 1M
332,84 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackLatencyThroughputUptime
SiliconFlowUnited States89,87 DA332,84 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-v3.1-terminus
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-v3.1-terminus",
    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_kfrequency_penalty

Reasoning

Let it think before answering — and see the thinking.

reasoninginclude_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 V3.1 Terminus

  • How much does DeepSeek V3.1 Terminus cost in dinars?

    About 0,26 DA per message. ↑ 89,87 DA · ↓ 332,84 DA per 1M tokens.

  • Is DeepSeek V3.1 Terminus 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 V3.1 Terminus best for?

    DeepSeek V3.1 Terminus is a maintenance release of V3.1 that fixes replies mixing languages and strengthens agents that write code and agents that search. It keeps the choice between thinking and answering directly, reads about 160 pages of text and allows replies up to about 147 pages. Use it for agents that browse, search and edit code, and for multilingual answers that must stay in one language. DeepSeek V3.2 is the next generation.

  • How do I pay for DeepSeek V3.1 Terminus without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, DeepSeek V3.1 Terminus included, is paid from that balance. No foreign card, no conversion.

  • Does DeepSeek V3.1 Terminus work in Arabic, French or Darja?

    DeepSeek mentions only Chinese and English, noting fewer mix-ups between the two. Arabic, French and Darja are not named.

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

    It reads text. Up to 164K tokens in one request, about 160 pages. It writes up to 111 000 words at once.

  • Is DeepSeek V3.1 Terminus open source?

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

  • Who makes DeepSeek V3.1 Terminus, and when was it released?

    DeepSeek. Released 22 September 2025. It knows the world up to 31 March 2025.

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