Hormouz AIHormouzSign in

Morph: Morph V3 Large: AI model

Morph V3 Large is a high-accuracy apply model for complex code edits at around 4,500 tokens/sec. Reachable from inside Iran through Hormouz.

Context window:
262,144 tokens
Input:
$0.9/1M tokens
Output:
$1.9/1M tokens
Type:
text
  • Streaming
  • Long context

Morph V3 Large is a specialized apply model that merges AI-suggested edits straight into source code with high accuracy. It is designed for precise code transformations and runs at around 4,500 tokens/sec.

To use it, the prompt must follow a specific format containing the instruction, the initial code and the edit snippet. Morph V3 Large has a context window of up to 262K tokens and is served through Hormouz behind an OpenAI-compatible API.

Pricing is usage-based: $0.90 per million input tokens and $1.90 per million output tokens. Hormouz provides stable access to the model from inside Iran.

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following format: <instruction>{instruction}</instruction> <code>{initial_code}</code>...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "morph/morph-v3-large",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorMorph
TypeText
Context window262,144 tokens
Pricing$0.90/M in · $1.90/M out
APIChat Completions
CapabilitiesStreaming

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "morph/morph-v3-large",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="morph/morph-v3-large",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "morph/morph-v3-large",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Morph: Morph V3 Large API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Morph: Morph V3 Large and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Morph V3 Large cost?
Billing is usage-based: $0.90 per million input tokens and $1.90 per million output tokens.
How do I access Morph V3 Large from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Morph V3 Large compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What is Morph V3 Large built for?
It is a specialized apply model for precisely merging suggested edits into source code, and it runs fast.
What prompt format does Morph V3 Large expect?
The prompt must contain the instruction, initial code and edit snippet in the specified format; the context window is up to 262K tokens.

Updated 2026-10-13