Hy3

基于真实业务场景打磨，兼具效果和性价比，强化 Coding、长文、推理和 Agent 等能力。

Model ID: hy3 · Type: chat · Provider: Tencent

Pricing

Capabilities

• reasoning
• function_calling
• prompt_caching

from openai import OpenAI

client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
    model="hy3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does Hy3 cost on yidun.ai 易盾.ai?

Hy3 (`hy3`) is billed per usage at $0.066/1M in · $0.264/1M out, in USD. Current pricing is always listed at https://yidun.ai/models/hy3.

How do I call Hy3 through yidun.ai 易盾.ai?

Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "hy3"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

What is Hy3's context window?

Hy3 accepts up to 192,000 input tokens and can return up to 128,000 output tokens. Requests exceeding the input limit are rejected before reaching the model.

What can Hy3 do?

Hy3 supports: function_calling, prompt_caching, reasoning.

Who makes Hy3?

Hy3 is a chat model from Tencent, available through the yidun.ai 易盾.ai gateway with the same API key as every other model.

Call it through the yidun.ai 易盾.ai OpenAI-compatible endpoint (API base: https://api.router.ai/v1). AI agents can discover and call every model on this gateway through MCP (https://mcp.router.ai/mcp) with no manual integration.

API reference · All models