Hy4 preview

混元Hy4 preview总参数770B、激活参数49B，重点面向Agent、Coding与生产力场景优化，强化复杂任务中的理解、规划、工具调用与持续执行能力。

Model ID: hy4-preview · Type: chat · Provider: Tencent

Endpoints: /v1/chat/completions · /v1/messages · /v1/responses

Pricing

Input (per 1M tokens)$0.3753 USD
Output (per 1M tokens)$1.12545 USD
Cache read (per 1M tokens)$0.0189 USD
from openai import OpenAI

client = OpenAI(api_key="sk-...", base_url="https://api.router.ai/v1")
resp = client.chat.completions.create(
    model="hy4-preview",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

FAQ

How much does Hy4 preview cost on 370.AI?

Hy4 preview (`hy4-preview`) is billed per usage at $0.3753/1M in · $1.12545/1M out, in USD. Current pricing is always listed at https://www.370.ai/models/hy4-preview.

How do I call Hy4 preview through 370.AI?

Send a request to https://api.router.ai/v1/v1/chat/completions with the header `Authorization: Bearer <your API key>` and `"model": "hy4-preview"`. The API is OpenAI-compatible, so any OpenAI SDK works by changing base_url to https://api.router.ai/v1 — no other code change.

Which endpoints does Hy4 preview support?

Hy4 preview can be called on: /v1/chat/completions; /v1/messages; /v1/responses.

What is Hy4 preview's context window?

Hy4 preview accepts up to 983,040 input tokens and can return up to 65,536 output tokens. Requests exceeding the input limit are rejected before reaching the model.

What can Hy4 preview do?

Hy4 preview supports: function_calling, prompt_caching.

Who makes Hy4 preview?

Hy4 preview is a chat model from Tencent, available through the 370.AI gateway with the same API key as every other model.

Call it through the 370.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