DeepSeek

Connect to DeepSeek's powerful reasoning and coding models.

Configuration

Field	Required	Example
Application Name	Yes	my-deepseek-app
Model Name	Yes	deepseek-chat, deepseek-reasoner
API Key	Yes	sk-...

Getting Your API Key

1. Go to DeepSeek Platform
2. Sign up or log in
3. Navigate to API Keys
4. Create and copy your API key

Popular Models

Model	Description
deepseek-chat	General-purpose chat powered by DeepSeek-V3.1
deepseek-reasoner	Advanced reasoning with thinking mode

Model Versions

Version	Description
DeepSeek-V3.1	Hybrid architecture with thinking/non-thinking modes, 671B params (37B active), 128K context
DeepSeek-R1	Reasoning model comparable to OpenAI o1, supports function calling
DeepSeek-R1-0528	Updated R1 with system prompts, JSON output, reduced hallucinations

Note: DeepSeek-V3.1 combines strengths of V3 and R1, surpassing prior models by 40%+ on SWE-bench.

For the complete list of available models and pricing, visit the DeepSeek API Documentation.

Advanced Parameters

Parameter	Type	Description
max_tokens	integer	Maximum tokens
temperature	float	Randomness
top_p	float	Nucleus sampling
frequency_penalty	float	Reduce repetition
presence_penalty	float	Encourage new topics
stop	array	Stop sequences

Setup Steps

1. Navigate to AI Applications → New Application
2. Select Model Providers tab
3. Click DeepSeek
4. Enter your Application Name and API Key
5. Select your desired Model Name
6. Configure Advanced Settings (optional)
7. Click Test Response to verify (optional)
8. Review and submit