PipeLLM logo
Back to approved models

Approved model profile_

Tencentactive

Hy3

Hy3 is Tencent's mixture-of-experts model for reasoning, software development, and agent workflows. It is designed to follow instructions across extended conversations and maintain the constraints needed for complex, multi-step work. Its text-based capabilities suit coding assistance, document...

hy3
Open Relay View integration
relay/request.mjsready to route
const completion = await client.chat.completions.create({
  model: "hy3",
  messages: [
    { role: "user",
      content: "Plan a multi-step task" }
  ]
});
policy checked provider selected
CONTEXT256K contextprompt window
MAX OUTPUT128Kper response
INPUT$0.15 / Mtoken price
OUTPUT$0.59 / Mtoken price

Route configuration_

Use the model through the contract you already have.

PipeLLM resolves provider access, policy, and supported model capabilities without changing the interface your application calls.

ENDPOINThttps://api.pipellm.aiOne base URL for OpenAI, Anthropic, and Gemini.

FORMAT ROUTES

OPENAI/openai
ANTHROPIC/anthropic
GEMINI/gemini
Use a format route to normalize requests and responses.
MODEL IDhy3Use this in every request
GOVERNANCEPolicy controlledApprovals and tool rules apply
PROVIDER AVAILABILITY1 route
ProviderContextMax outputDiscountInput / MOutput / M
Tokenhub256K context128K—$0.15 / M$0.59 / M
Displayed pricing is per one million tokens and may vary by provider.
SUPPORTED SURFACESactive
input: textoutput: texttool use

Relay governs model access with the same routing policy that Lens keeps visible and auditable.