[Tencent Cloud](/ai-gateway/models/labs/tencent)

# Hy3

Hy3 is an Apache 2.0 Mixture-of-Experts model from the Tencent Cloud Hunyuan team, with 295B total parameters, 21B active per token, and three selectable reasoning levels. It supports a context window of 262.1K tokens and a max output of 262.1K tokens per request.

Input and output price

Prices from: Input $0.13, Output $0.52, Per 1M tokens

24h uptime

Loading AI Gateway uptime

[Get API key](https://vercel.com/d?to=%2F%5Bteam%5D%2F~%2Fai-gateway%3FshowCreateKeyModal%26utm_source%3Dgateway-model-page%26utm_campaign%3Dai-gateway-models&title=Get%20API%20key) [Read the docs](https://vercel.com/docs/ai-gateway)

AI SDKChat CompletionsMessagesResponses

```
1import { streamText } from 'ai'
2

3const result = streamText({
4  model: 'tencent/hy3',
5  prompt: 'Why is the sky blue?'
6})
```

[Read docs](https://vercel.com/docs/ai-gateway/sdks-and-apis/ai-sdk)

[Overview](/ai-gateway/models/hy3) [API](/ai-gateway/models/hy3/api) [Providers](/ai-gateway/models/hy3/providers) [Uptime](/ai-gateway/models/hy3/uptime) [Status](/ai-gateway/models/hy3/status) [Throughput](/ai-gateway/models/hy3/throughput) [Latency](/ai-gateway/models/hy3/latency) [Similar](/ai-gateway/models/hy3/similar) [About](/ai-gateway/models/hy3/about) [FAQ](/ai-gateway/models/hy3/faq)

## [Copy link to heading](#about-hy3)About Hy3

Tencent Cloud released Hy3 on July 6, 2026 under the Apache 2.0 license, publishing BF16 and FP8 weights on Hugging Face, ModelScope, GitCode, and CNB. Hy3 comes out of the Hunyuan line and follows the Hy3 Preview release from late April 2026.

The architecture is a Mixture-of-Experts (MoE) with 295B total parameters and 21B active per token, spread across 80 layers and 192 routed experts with top-8 routing. Attention is grouped-query with 64 heads and eight key-value heads. A separate 3.8B multi-token prediction layer drafts more than one token per forward pass, which serving stacks use for speculative decoding. The context window is 262.1K tokens, and one request can return up to 262.1K tokens.

Reasoning depth is a per-request setting. The `reasoning_effort` field accepts `no_think` for a direct answer, `low` for shallow reasoning, and `high` for deep chain-of-thought on math, coding, and analysis. `no_think` is the default, so you opt into reasoning tokens rather than paying for them on every call.

Tencent Cloud focused on tool-call and output-format stability, drawing on feedback from more than 50 of its own products. On SWE-Bench Verified, Hy3 holds accuracy variance within 4% across agent scaffoldings including CodeBuddy, Cline, and KiloCode, so a result from one harness carries to another. Internal evaluations built on real-world scenarios put the hallucination rate at 5.4%, down from 12.5%, and the commonsense error rate at 12.7%, down from 25.4%. On a multi-turn suite covering coreference resolution, ellipsis recovery, and constraint inheritance, the issue rate fell from 17.4% to 7.9%.

Tencent Cloud also ran a blind evaluation in which 270 experts scored tasks drawn from their own work. Hy3 averaged 2.67 out of four against GLM-5.1 at 2.51, with the widest margins on frontend development, data and storage, and CI/CD tasks.

Call Hy3 with one API key and get provider routing, automatic failover, and built-in observability. Integrate through the AI SDK, the Chat Completions API, the Responses API, the Messages API, or other supported API formats. Pay $0.126 per million input tokens, $0.522 per million output tokens, and $0.0315 per million cached input tokens at current list rates.

Your use is subject to Tencent Cloud's [Terms](https://www.tencentcloud.com/document/product/301/78869) & [Privacy](https://www.tencentcloud.com/document/product/1300/78952) Policies.