Skip to main content

​
What is Fast Apply?

The Apply Model intelligently merges your original code with update snippets at 98% accuracy and 10,500+ tokens/second. Companies like Cursor use this method for fast, reliable edits. Methods like search and replace face high error rates and are slower because they need to output negative tokens and positive tokens. Unlike diff-based methods, it preserves code structure, comments, and syntax while understanding context semantically.

Try the API Playground

Test the Apply Model instantly with live examples

​
Why Choose Fast Apply?

  • Ultra-fast: 10,500 tokens/sec
  • High accuracy: 98% success rate in one pass
  • Token efficient: Processes only changed sections

​
Models

ModelSpeedAccuracyBest For
morph-v3-fast10,500+ tok/sec96%Real-time edits
morph-v3-large2500+ tok/sec98%Production systems
autoVariable~98%Automatic selection

​
Quick Start

1

Setup Client

Python
from openai import OpenAI

client = OpenAI(
    api_key="your-morph-api-key",
    base_url="https://api.morphllm.com/v1"
)
2

Apply Changes

Python
def apply_edit(instruction: str, original: str, update: str):
    response = client.chat.completions.create(
        model="morph-v3-fast",
        messages=[{
            "role": "user",
            "content": f"<instruction>{instruction}</instruction>\n<code>{original}</code>\n<update>{update}</update>"
        }]
    )
    return response.choices[0].message.content

# Example
original = """
const a = 1
const authenticateUser = () => {
  return "Authenticated"
}
"""
# These should be coming from your Agent
instruction = "I will change the return text to be French"
update = """
// ... existing code ...
  return "Authentifié"
}
"""

final_code = apply_edit(instruction, original, update)

​
Best Practices

Update Snippets: Use // ... existing code ... for unchanged sections: 
// Good
const authenticateUser = async (email, password) => {
  // ... existing code ...
  const result = await verifyUser(email, password)
  return result ? "Authenticated" : "Unauthenticated"
}
Instructions: Have the agent write clear, first-person descriptions to “disambiguate uncertainty in the edit”:
  • ✅ “I will add async/await error handling”
  • ❌ “Change this function”

​
Next Steps

API Reference

Complete technical reference and error handling

Build AI Tools

Integration guide for AI agents