DeepSeek
DeepSeek V4 Pro, DeepSeek V4 Flash, DeepSeek-R1 and more — high-performance, cost-efficient models
DeepSeek is an AI lab offering powerful open-weight models via a commercial API. DeepSeek V4 Pro is their latest flagship with significantly improved reasoning and coding, while V4 Flash delivers the same generation at higher throughput and lower cost. DeepSeek-R1 is a chain-of-thought reasoning model that matches leading models at a fraction of the price, and DeepSeek-V3 (deepseek-chat) is the proven general-purpose workhorse.
Official documentationAvailable Models
DeepSeek V4 Pro
DeepSeek's latest flagship model. Significantly improved reasoning, coding, and instruction-following over V3.
Best for: Advanced reasoning, code generation, complex analysis
DeepSeek V4 Flash
Faster, cost-efficient variant of DeepSeek V4 Pro. Optimised for high-throughput production workloads.
Best for: High-volume pipelines, cost-efficient inference
DeepSeek-R1
A reasoning model using chain-of-thought, comparable to o3 at much lower cost.
Best for: Math, science, logical reasoning
DeepSeek-V3
General-purpose chat model. Excellent at code, writing, and instruction following.
Best for: General tasks, code generation
Setup
Create a DeepSeek Platform account
Create a DeepSeek Platform account
Sign up at platform.deepseek.com. Add a payment method or apply for credits.
DeepSeek PlatformGenerate an API key
Generate an API key
Navigate to API Keys in the dashboard, click Create new API key, name it, and copy the value.
Add the provider in CipherSense
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.
| Field | Required | Description |
|---|---|---|
| API Key | Required | Your DeepSeek API key from platform.deepseek.com. |
Common Use Cases
Ready to add DeepSeek?
Configure this provider in your Organisation Settings and use it in any workflow.