opendunes

Mercury 2

by InceptionReleased 4 March 2026

Mercury 2 thinks before it answers and writes by refining a whole stretch of text at once instead of word by word, so it produces over a page of text every second. You send up to 128 pages of text, and it can use your tools or fill in an exact form you give it. Use it where waiting adds up: voice assistants, live search and coding helpers that call the model many times.

TakesText
GivesText
Open in chatCreate API keyCompare

What it costs

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

≈ 0,21 DA per message3 000 DA buys about 14 000 messages

One message, the ordinary use

1 000 tokens sent× 83,21 DA per 1M0,083 DA
500 tokens back× 249,63 DA per 1M0,12 DA
Total≈ 0,21 DA

Every rate

Meter↑ you send↓ comes back
Text tokens83,21 DA249,63 DA
Cached tokens read8,32 DA

per 1M tokens

Answer a quick question≈ 0,075 DA
Reply to a customer email≈ 0,15 DA
Write a one-page draft≈ 0,25 DA
Translate a full page of text≈ 0,26 DA
Explain a stack trace and suggest a fix≈ 0,27 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.

Inception…
↑ Sent, per 1M
83,21 DA
↓ Back, per 1M
249,63 DA
Cache read
8,32 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackCache readLatencyThroughputUptime
Inception83,21 DA249,63 DA8,32 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
inception/mercury-2
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="inception/mercury-2",
    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_tokenstemperaturestop

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 Mercury 2

  • How much does Mercury 2 cost in dinars?

    About 0,21 DA per message. ↑ 83,21 DA · ↓ 249,63 DA per 1M tokens.

  • Is Mercury 2 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 Mercury 2 best for?

    Mercury 2 thinks before it answers and writes by refining a whole stretch of text at once instead of word by word, so it produces over a page of text every second. You send up to 128 pages of text, and it can use your tools or fill in an exact form you give it. Use it where waiting adds up: voice assistants, live search and coding helpers that call the model many times.

  • How do I pay for Mercury 2 without an international card?

    Deposit dinars with your Edahabia or CIB card. Every model, Mercury 2 included, is paid from that balance. No foreign card, no conversion.

  • Does Mercury 2 work in Arabic, French or Darja?

    Inception names no languages for Mercury 2. Arabic, French and Darja: not stated.

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

    It reads text. Up to 128K tokens in one request, about 120 pages. It writes up to 38 000 words at once.

  • Is Mercury 2 open source?

    No. Inception has not published its weights.

  • Who makes Mercury 2, and when was it released?

    Inception. Released 4 March 2026.

Other Inception models, priced in dinars

See all Inception models
Mercury DecideInception · Sep 30, 2026

Mercury Decide takes a situation written as text, with pictures if you like, plus questions of a fixed kind. For each question it gives back a yes or no, a pick from options, or a numeric score, with a probability worked out inside the model and no written answer. It handles up to 14 decisions a second, so you can run every case through it and send doubtful ones to a person. Kev 4B is the alternative you can download and run yourself, for situations that are text only.

65 pages per call
≈0,0067 DAper case
View model
Mercury 3Inception · Oct 16, 2026

Mercury 3 is a diffusion-based text model that thinks first and calls your tools, built for agentic workflows and real-time work where latency compounds, with a million-token window and JSON output

Thinks firstUses your tools1 000 pages at once
≈0,092 DAper message
View model
Mercury 2.5Inception · Sep 8, 2026

Mercury 2.5 writes by refining a whole stretch of text at once instead of word by word, reaching more than a page of text every second, and it thinks at a level you set. You send up to 260 pages of text, with tools or an exact form to fill in, and it can use several tools at the same time. Use it in coding helpers, search helpers and voice systems, where each model call adds delay.

Thinks firstUses your tools260 pages at once
≈0,038 DAper message
View model