Skip to content

Hy3 · Incognito

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use.

Pricing

Input
$0.1575per 1M tokens
Output
$0.672per 1M tokens
Cache read
$0.042per 1M tokens
Max output
235,929tokens

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": { "tencent/hy3:incognito": { "limit": { "context": 262144, "output": 235929 } } }
    }
  }
}
OpenCode, set up for Hy3 · Incognito