opendunes

Morph V3 Fast (batch)

by MorphReleased 7 July 2025

Morph V3 Fast does not write code from scratch, it applies an edit. You send an instruction, the original code and a short update marked in a fixed three-tag format, and it merges the update into the file and hands back the result at about 10 pages of code a second. That suits a coding assistant that proposes partial edits and needs them applied quickly. Morph V3 Large works at about 4 pages a second and is built for complex edits.

TakesText
GivesText

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.

MorphUnited States…
↑ Sent, per 1M
133,13 DA
↓ Back, per 1M
199,70 DA
Latency
…
Throughput
…
Provider↑ Sent↓ BackLatencyThroughputUptime
MorphUnited States133,13 DA199,70 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.

≈ 0,23 DA per message3 000 DA buys about 12 000 messages

One message, the ordinary use

1 000 sent1 000 tokens sent× 133,13 per 1M× 133,13 DA per 1M0,13 DA
500 back500 tokens back× 199,70 per 1M× 199,70 DA per 1M0,10 DA
Total≈ 0,23 DA

Every rate

Meter↑ you send↓ comes back
Text tokens133,13 DA199,70 DA

per 1M tokens

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
morph/morph-v3-fast: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="morph/morph-v3-fast: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_tokenstemperaturestop

Limits

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

Context window
81 920 tokens
Max output
38 000 tokens
Reads at once
≈ 81 pages
Longest reply
≈ 29 000 words
Tokenizer
Other
Released
7 Jul 2025
Full API reference

Questions about Morph V3 Fast (batch)

How much does Morph V3 Fast (batch) cost in dinars?

About 0,23 DA per message. ↑ 133,13 DA · ↓ 199,70 DA per 1M tokens.

Is Morph V3 Fast (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 Morph V3 Fast (batch) best for?

Morph V3 Fast does not write code from scratch, it applies an edit. You send an instruction, the original code and a short update marked in a fixed three-tag format, and it merges the update into the file and hands back the result at about 10 pages of code a second. That suits a coding assistant that proposes partial edits and needs them applied quickly. Morph V3 Large works at about 4 pages a second and is built for complex edits.

How do I pay for Morph V3 Fast (batch) without an international card?

Add credit in dinars with your Edahabia or CIB card. Every model, Morph V3 Fast (batch) included, is paid from that balance. No foreign card, no conversion.

Does Morph V3 Fast (batch) work in Arabic, French or Darja?

Morph names no languages for Morph V3 Fast (batch). Arabic, French and Darja: not stated.

Can it read PDFs, images or a whole book?

It reads text. Up to 82K tokens in one request, about 81 pages. It writes up to 29 000 words at once.

Is Morph V3 Fast (batch) open source?

No. Morph has not published its weights.

Who makes Morph V3 Fast (batch), and when was it released?

Morph. Released 7 July 2025.

Other Morph models, priced in dinars

See all Morph models
ReflexMorph · Nov 3, 2026

This model takes in text, reads about 65 pages at once, and gives back short typed answers that can run to 58 pages. Its best use is putting a fixed list of questions to one long case file and getting a pick, a named thing or a score back for each. Questions asked again about the same file reuse the stored reading, so a batch of questions on one file costs less after the first. It does not handle pictures, sound or video, and it does not write essays, so jobs needing those call for a different kind of model.

65 pages per call
≈0,014 DAper case
View model
Morph V3 FastMorph · Jul 7, 2025

Morph V3 Fast does not write code from scratch, it applies an edit. You send an instruction, the original code and a short update marked in a fixed three-tag format, and it merges the update into the file and hands back the result at about 10 pages of code a second. That suits a coding assistant that proposes partial edits and needs them applied quickly. Morph V3 Large works at about 4 pages a second and is built for complex edits.

260 pages at onceFills your JSON
≈0,47 DAper message
View model
Morph V3 LargeMorph · Jul 7, 2025

Morph V3 Large applies code edits rather than writing code. You send an instruction, the original code and an edit marked in a fixed three-tag format, and it hands back the merged file at about 4 pages of code a second. It is the one built for complex edits, where the merge has to land precisely.

260 pages at onceFills your JSON
≈0,62 DAper message
View model
Morph V3 Large (batch)Morph · Jul 7, 2025

Morph V3 Large applies code edits rather than writing code. You send an instruction, the original code and an edit marked in a fixed three-tag format, and it hands back the merged file at about 4 pages of code a second. It is the one built for complex edits, where the merge has to land precisely.

260 pages at onceFills your JSON
≈0,31 DAper message
View model