Skip to content

DeepSeek V4.1 Flash · Incognito

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.

Pricing

Input
$0.2205per 1M tokens
Output
$0.882per 1M tokens
Cache read
$0.0044per 1M tokens
Max output
943,718tokens

Phala's price plus a 5% routing fee. Deference adds no markup.

opencode.json

{
  "provider": {
    "deference": {
      "npm": "@ai-sdk/openai-compatible",
      "options": { "baseURL": "https://deference.si/v1", "apiKey": "{env:DEFERENCE_API_KEY}" },
      "models": { "deepseek/deepseek-v4.1-flash:incognito": { "limit": { "context": 1048576, "output": 943718 } } }
    }
  }
}
OpenCode, set up for DeepSeek V4.1 Flash · Incognito