Skip to content

Qwen3.8 27B · Incognito

Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

Pricing

Input
$0.21per 1M tokens
Output
$2.63per 1M tokens
Cache read
$0.0525per 1M tokens
Max output
262,144tokens

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": { "qwen/qwen3.8-27b:incognito": { "limit": { "context": 1000000, "output": 262144 } } }
    }
  }
}
OpenCode, set up for Qwen3.8 27B · Incognito