Prefix Completion - MyTokenGate

1. Use Cases

In prefix completion, the user provides the desired prefix information, allowing the model to complete the rest of the content based on the prefix provided by the user. With this capability, the model demonstrates better instruction-following abilities and can address user requirements for specific formats in certain scenarios.

2. How to Use

Add the extra_body parameter to your request:

extra_body={"prefix": "desired prefix content"}

3. Supported Models

Most large language models support this parameter. For reasoning models like Qwen3 series, add enable_thinking=true to disable reasoning mode first. DeepSeek R1 series does not currently support this parameter.

View the full model list at Model List 

4. Example Usage

Below is an example of using prefix completion with the OpenAI library:

from openai import OpenAI
 
client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://gateway.mytokengate.com/v1"
)
 
messages = [
    {"role": "user", "content": "Write a quick sort function"}
]
 
response = client.chat.completions.create(
    model="gpt-4o",
    messages=messages,
    extra_body={"prefix": "```python\n"}
)
 
print(response.choices[0].message.content)