AgentSky
Log inSign up

Hy3

by Tencent
tencent/hy3

Hy3 is a text-input model by Tencent, available through the AgentSky API as tencent/hy3 at $0.153186 per million input tokens and $0.612744 per million output tokens, with a 262K context window.

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.

  1. Get an API key

  2. Send a request

    curl https://gateway.agentsky.dev/v1/chat/completions \
  -H "authorization: Bearer $AGENTSKY_API_KEY" \
  -H "content-type: application/json" \
  -d '{"model":"tencent/hy3","messages":[{"role":"user","content":"In one sentence, what can you help me with?"}],"max_tokens":128}'

  3. Run it here, no terminal needed

    Billed to your balance: under $0.01.

  4. Or hand it to your agent

    Use Hy3 through AgentSky.
Model id: tencent/hy3
OpenAI-compatible base URL: https://gateway.agentsky.dev/v1 · Anthropic base URL: https://gateway.agentsky.dev
Docs: https://agentsky.dev/models/tencent/hy3.md
Key: <your AgentSky API key>
SDK samples ↓API docs ↗

This model is available through the API. It is not currently offered as an agent’s reasoning model.

Pricing

USD per million tokens, using your plan when signed in.
MeterPer 1M tokens
InputPrice: $0.153186
OutputPrice: $0.612744
Cache readPrice: $0.038297
Cache writePrice: $0.153186

Every response carries its own cost. Balance and per-call records: /v1/credits and /v1/generation.

Use it

Point your client at the gateway and pass this model id. Nothing else changes.
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://gateway.agentsky.dev/v1",
  apiKey: process.env.AGENTSKY_API_KEY, // ast_…
});

const completion = await client.chat.completions.create({
  model: "tencent/hy3",
  messages: [{ role: "user", content: "Summarise this ticket." }],
});
console.log(completion.usage.cost); // USD, in the response

Questions