Skip to main content
DeepSeek models can be configured directly in Langdock using the DeepSeek API.

​
Prerequisites

Before setting up DeepSeek models, you need:
  1. A DeepSeek account at platform.deepseek.com
  2. An API key from the DeepSeek platform
  3. Admin access to your Langdock workspace

​
Setup Steps

  1. Go to the model settings and click on Add Model
  2. Configure the Display Settings:
    • Provider: DeepSeek
    • Model name: The model you want to add
    • Hosting provider: DeepSeek
    • Region: US (DeepSeek’s API is hosted in the US)
    • Image analysis: Disabled (DeepSeek models do not support vision)
  3. Configure the Model Configuration:
    • SDK: Select DeepSeek
    • Base URL: https://api.deepseek.com/v1
    • Model ID: Use the official model identifier (e.g., deepseek-reasoner for R1, deepseek-chat for V3)
    • API key: Paste your DeepSeek API key
    • Context Size: Set according to the model (check DeepSeek’s documentation for current values)
  4. For reasoning models (like DeepSeek R1), enable Display Thinking to show the model’s reasoning process in the UI.
  5. Click Save and test the model by sending a prompt before making it visible to all users.

​
Model IDs

DeepSeek uses two main model identifiers:
Model IDType
deepseek-reasonerReasoning model (R1 series) — excels at step-by-step problem solving and coding
deepseek-chatGeneral-purpose model (V3 series) — fast responses, good for everyday tasks
Check DeepSeek’s API docs for the latest available models and their specifications.

​
Configuration Notes

  • DeepSeek models are hosted in the US region only
  • DeepSeek R1 is a reasoning model — enable Display Thinking to see its reasoning steps
  • The base URL must include the /v1 path: https://api.deepseek.com/v1

​
Troubleshooting

Model not responding:
  • Verify your API key is valid and has not expired
  • Check that you have sufficient credits in your DeepSeek account
  • Ensure the model ID matches exactly (case-sensitive)
Slow responses:
  • DeepSeek R1 (reasoning model) may take longer due to its step-by-step reasoning process
  • Consider using DeepSeek V3 for faster responses on simpler tasks
If you run into any issues, contact support@langdock.com.