Hy4 preview · requesty

Hy4 preview is Tencent's flagship class MoE model with 770B total parameters and 49B activated, supporting a 1M token context window. It is optimized for agent, coding, and productivity scenarios, with strong task decomposition, context tracking, instruction following, and long chain execution. It is suited for coding agents, complex tool use, and multi step agentic workflows.

Modelo base Todos os modelos desta base Todos os modelos do provedor ao provedor

Entrada, $/1M $0.83

Saída, $/1M $2.50

Leitura de cache $0.042

Gravação de cache —

Contexto 1 048 576

Saída máx. 65 536

Aceita texto

Última verificação 04.11.2026 12:00:14 UTC

Fonte página do provedor

Alertas de preço

Entre para seguir o preço

API

API compatível com OpenAI: os SDKs oficiais da OpenAI funcionam com esta URL base. Substitua YOUR_API_KEY pela sua chave do provedor.

URL base da API	`https://router.requesty.ai/v1`
Endpoint	`https://router.requesty.ai/v1/chat/completions`
ID do modelo	`tencent/hy4-preview`

curl

curl https://router.requesty.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "tencent/hy4-preview", "messages": [{"role": "user", "content": "Hello!"}], "max_tokens": 256}'

Python

import requests

r = requests.post(
    "https://router.requesty.ai/v1/chat/completions",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
      "model": "tencent/hy4-preview",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ],
      "max_tokens": 256
    },
)
print(r.json())

JavaScript

const r = await fetch("https://router.requesty.ai/v1/chat/completions", {
  method: "POST",
  headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
  body: JSON.stringify({
    "model": "tencent/hy4-preview",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ],
    "max_tokens": 256
  }),
});
console.log(await r.json());

Requisição (JSON)

{
  "model": "tencent/hy4-preview",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 256
}

Resposta (JSON)

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "tencent/hy4-preview",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hi! How can I help?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

O endereço vem da lista de modelos do provedor; confira na documentação dele.

Documentação da API do provedor

Source: AI Rate Card, https://airatecard.com/pt/c/offer%3Arequesty%7Ctencent/hy4-preview, prices checked 2026-11-04; seller's page: https://www.requesty.ai/models/tencent/hy4-preview

Dados técnicos

ID: offer:requesty|tencent/hy4-preview