Hy4

Tencent: Hy4 is Tencent's mixture-of-experts flagship, the GA successor to Hy4 preview.

Input / output priceUp to 60% off: ~~$0.834 / $2.501~~$0.3336 / $1.0004 per 1M
Context: 1M tokens
Released: Nov 3, 2026

Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "tencent/hy4".

from openai import OpenAI

client = OpenAI(

    base_url="https://api.respan.ai/api/",

    api_key="YOUR_RESPAN_API_KEY",

)

response = client.chat.completions.create(

    model="tencent/hy4",

    messages=[{"role": "user", "content": "Hello!"}],

)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({

  baseURL: "https://api.respan.ai/api/",

  apiKey: "YOUR_RESPAN_API_KEY",

});

const response = await client.chat.completions.create({

  model: "tencent/hy4",

  messages: [{ role: "user", content: "Hello!" }],

});

console.log(response.choices[0].message.content);

curl https://api.respan.ai/api/chat/completions \

  -H "Authorization: Bearer YOUR_RESPAN_API_KEY" \

  -H "Content-Type: application/json" \

  -d '{

    "model": "tencent/hy4",

    "messages": [{"role": "user", "content": "Hello!"}]

}'

Read docs

Providers

2 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

Provider	Context	Input	Output	Cache read	Capabilities
Tencent60% off`tencent/hy4`	1M	~~$0.834/M~~$0.3336/M	~~$2.501/M~~$1.0004/M	~~$0.042/M~~$0.0168/M
OpenRouter`openrouter/hy4`	1M	$0.417/M	$1.2505/M	$0.021/M

Is a provider down? OpenRouter status

Pricing

Averaged across 2 providers, in USD per 1M tokens after gateway discounts.

Average input: $0.38 per 1M
Average output: $1.13 per 1M
Average cache read: $0.02 per 1M

Cost by volume

Total cost from 0 to 1T tokens on the cheapest and most expensive provider.

Highest$0.417/MOpenRouterLowest$0.3336/MTencent

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

843tokens/sacross providers

Faster than 94% of the other 330 models on the gateway

Time to first token

Lower is better

31sacross providers

Faster than 2% of the other 94 models on the gateway

Response latency

Lower is better

26sacross providers

Faster than 10% of the other 377 models on the gateway

Apps

Use Hy4 in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Hy4 FAQ

Short answers, built from the data on this page.

Hy4 is a model from Tencent, released on Nov 3, 2026. Tencent: Hy4 is Tencent's mixture-of-experts flagship, the GA successor to Hy4 preview.

On the Respan gateway, Hy4 costs from $0.3336 per 1M input tokens and $1.0004 per 1M output tokens on Tencent, after gateway discounts. Averaged across its 2 providers, it costs $0.38 per 1M input tokens and $1.13 per 1M output tokens.

Hy4 is available through 2 providers: Tencent and OpenRouter.

Hy4 accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "tencent/hy4". To set it up with a coding agent, copy the agent setup prompt at the top of this page.