Tencent: Hy3

Chat
tencent/hy3
Created Aug 21, 2026|262K context|$0.15/M input tokens|$0.64/M output tokens|$0.04/M cache read

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. It supports a configurable reasoning effort.

Providers for Tencent: Hy3

RedPill routes this private model across verified providers with automatic fallbacks. Pricing is unified, so you pay the same price no matter which provider serves your request, while live metrics show first-token latency, speed, and uptime.

Total Context
262K
Input
$0.15/M
Output
$0.64/M
Cache Read
$0.04/M
ProviderFirst TokenSpeedUptime
redpill
CheckingCheckingChecking

Gateway API

RedPill provides a unified private completion API to all models and providers that you can call directly, or through the OpenAI SDK. Verification can be added without changing your model call pattern.

const response = await fetch("https://api.redpill.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${process.env.REDPILL_API_KEY}`,
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "tencent/hy3",
    "messages": [
      {
        "role": "user",
        "content": "What is the meaning of life?"
      }
    ],
    "provider": { "aci_verified": true }
  })
});

console.log("receipt", response.headers.get("x-receipt-id"));
console.log(await response.json());
RedPill

End-to-end encrypted AI through one gateway: private models, verified providers, unified pricing, live performance, and evidence your team can check.