Unitalk
Store
Back to Discovery
DeepSeekDeepSeek
@DeepSeek
2 models
DeepSeek is a company focused on the research and application of artificial intelligence technology. Its latest model, DeepSeek-V2.5, integrates general conversational and code processing capabilities, achieving significant enhancements in human preference alignment, writing tasks, instruction following, and more.

Supported Models

DeepSeek
DeepSeek

DeepSeek V3

deepseek-chat
64K
Maximum Context Length
64K
Maximum Output Length
--
Input Price
$0.14
Output Price
$0.28
DeepSeek

DeepSeek R1

deepseek-reasoner
64K
Maximum Context Length
64K
Maximum Output Length
--
Input Price
$0.56
Output Price
$2.24

Using DeepSeek in LobeChat

Using DeepSeek in LobeChat

DeepSeek is an advanced open-source Large Language Model (LLM). The latest version, DeepSeek-V2, has made significant optimizations in architecture and performance, reducing training costs by 42.5% and inference costs by 93.3%.

This document will guide you on how to use DeepSeek in LobeChat:

Step 1: Obtain DeepSeek API Key

  • First, you need to register and log in to the DeepSeek open platform.
New users will receive a free quota of 500M Tokens
  • Go to the API keys menu and click on Create API Key.
Create Deepseek API Key
  • Enter the API key name in the pop-up dialog box.
Enter Deepseek API Name
  • Copy the generated API key and save it securely.
Save Deepseek API Key

Please store the key securely as it will only appear once. If you accidentally lose it, you will need to create a new key.

Step 2: Configure DeepSeek in LobeChat

  • Access the App Settings interface in LobeChat.
  • Find the setting for DeepSeek under Language Models.
Enter Deepseek API Key
  • Open DeepSeek and enter the obtained API key.
  • Choose a DeepSeek model for your assistant to start the conversation.
Select Deepseek Model

You may need to pay the API service provider during usage, please refer to DeepSeek's relevant pricing policies.

You can now engage in conversations using the models provided by Deepseek in LobeChat.

Related Providers

@Unitalk
19 models
Unitalk facilitates access to AI models via officially deployed APIs. It monitors model usage through a Credits system, where these Credits act as an equivalent to the Tokens used by LLMs
OpenAIOpenAI
@OpenAI
23 models
OpenAI is a leading global artificial intelligence research organization, with models like the GPT series pushing the frontiers of natural language processing. OpenAI is dedicated to transforming multiple industries through innovative and efficient AI solutions. Their products are characterized by significant performance and cost-effectiveness, widely used in research, business, and innovative applications.
OllamaOllama
@Ollama
45 models
Ollama offers a wide range of models covering code generation, mathematical operations, multilingual processing, and conversational interactions, catering to diverse needs for enterprise-level and localized deployments.
Anthropic
ClaudeClaude
@Anthropic
9 models
Anthropic is a company focused on AI research and development, providing a range of advanced language models such as Claude 3.5 Sonnet, Claude 3 Sonnet, Claude 3 Opus, and Claude 3 Haiku. These models strike an ideal balance between intelligence, speed, and cost, making them suitable for various applications, from enterprise workloads to fast-response scenarios. Claude 3.5 Sonnet, as its latest model, performs exceptionally well in multiple evaluations while maintaining high cost-effectiveness.
AWS
BedrockBedrock
@Amazon Bedrock
17 models
Bedrock is a service provided by Amazon AWS that focuses on offering advanced AI language models and visual models for enterprises. Its model family includes the Claude series from Anthropic and the Llama 3.1 series from Meta, covering a range from lightweight to high-performance options, supporting tasks such as text generation, conversation, and image processing, suitable for enterprise applications of various scales and needs.