WebInfer

🔍

DeepSeek

Reasoning models with context caching

Budget
Fast & Cost-Effective
API

Configure DeepSeek

Add your DeepSeek API key in Settings

Go to Settings
Capabilities
chat
reasoning
caching
Configuration Schema
Required and optional fields for configuring this provider
FieldTypeRequired
apiKey
password
Required
CLI Usage
For users running the daemon server locally or a self-hosted gateway

Add provider:

npx webinfer provider add deepseek --key YOUR_API_KEY

Test connection:

npx webinfer provider test deepseek

Get your API key from https://platform.deepseek.com/

Programmatic Usage
Use DeepSeek in your code with WebInfer

Basic usage:

import { generateText } from "webinfer"

// WebInfer automatically routes to the best available provider
const result = await generateText({
  prompt: "Write a haiku about programming"
})

console.log(result.text)

Specify DeepSeek explicitly:

import { generateText } from "webinfer"

const result = await generateText({
  prompt: "Write a haiku about programming",
  provider: "deepseek",
  model: "deepseek-chat"
})

console.log(result.text)
console.log("Provider:", result.provider)
console.log("Model:", result.model)

Streaming:

import { streamText } from "webinfer"

const { textStream } = await streamText({
  prompt: "Write a story about AI",
  provider: "deepseek"
})

for await (const chunk of textStream) {
  process.stdout.write(chunk)
}