DeepSeek API
๐Ÿ‡บ๐Ÿ‡ธ English
  • ๐Ÿ‡บ๐Ÿ‡ธ English
  • ๐Ÿ‡ฏ๐Ÿ‡ต Japanese
  • ๐Ÿ‡ฐ๐Ÿ‡ท Korea
  • ๐Ÿ‡ต๐Ÿ‡น Portuguese
  1. API Guides
DeepSeek API
๐Ÿ‡บ๐Ÿ‡ธ English
  • ๐Ÿ‡บ๐Ÿ‡ธ English
  • ๐Ÿ‡ฏ๐Ÿ‡ต Japanese
  • ๐Ÿ‡ฐ๐Ÿ‡ท Korea
  • ๐Ÿ‡ต๐Ÿ‡น Portuguese
  • Start quickly
    • Your First API Call
    • Models & Pricing
    • The Temperature Parameter
    • Token & Token Usage
    • Rate Limit
    • Error Codes
  • API Reference
    • Introduction
    • Create Chat Completion
      POST
    • Create FIM Completion (Beta)
      POST
    • Lists Models
      GET
    • Get User Balance
      GET
  • API Guides
    • Reasoning Model (deepseek-reasoner)
    • Multiple rounds of conversations
    • Chat Prefix Completion (Beta)
    • FIM Completion (Beta)
    • JSON Output
    • Function Calling
    • Context Caching
  • FAQ
    • FAQ
  1. API Guides

FIM Completion (Beta)

In FIM (Fill In the Middle) completion, users can provide a prefix and a suffix (optional), and the model will complete the content in between. FIM is commonly used for content completionใ€code completion.

Notice#

1.
The max tokens of FIM completion is 4K.
2.
The user needs to set base_url=https://api.deepseek.com/beta to enable the Beta feature.

Sample Code#

Below is a complete Python code example for FIM completion. In this example, we provide the beginning and the end of a function to calculate the Fibonacci sequence, allowing the model to complete the content in the middle.

Integration With Continue#

Continue is a VSCode plugin that supports code completion. You can refer to this document to configure Continue for using the code completion feature.
Modified atย 2025-02-06 08:35:06
Previous
Chat Prefix Completion (Beta)
Next
JSON Output
Built with