CipherSense Logo
DocsAgentsDeepSeek
deepseek
LLM Provider

DeepSeek

DeepSeek-R1 and DeepSeek-V3 — high-performance, cost-efficient models

DeepSeek is an AI lab offering powerful open-weight models via a commercial API. DeepSeek-R1 is a reasoning model that matches or exceeds leading models on benchmarks at a fraction of the cost. DeepSeek-V3 is their general-purpose chat model, optimised for instruction following and code tasks.

Official documentation

Available Models

DeepSeek-R1

128k tokens

A reasoning model using chain-of-thought, comparable to o3 at much lower cost.

Best for: Math, science, logical reasoning

DeepSeek-V3

128k tokens

General-purpose chat model. Excellent at code, writing, and instruction following.

Best for: General tasks, code generation

Setup

1

Create a DeepSeek Platform account

Sign up at platform.deepseek.com. Add a payment method or apply for credits.

DeepSeek Platform
2

Generate an API key

Navigate to API Keys in the dashboard, click Create new API key, name it, and copy the value.

3

Add the provider in CipherSense

Go to Organization Settings > LLM Providers > Add Provider. Select DeepSeek, paste your API key, and click Save.

Connection Fields

Fields required when adding this provider in Organization Settings › LLM Providers.

FieldRequiredDescription
API Key
Required
Your DeepSeek API key from platform.deepseek.com.

Common Use Cases

Cost-efficient reasoning tasksMath and scientific analysisCode generationText summarization

Ready to add DeepSeek?

Configure this provider in your Organisation Settings and use it in any workflow.

Open Dashboard ← Back to AI Agents