Hy3

General purposeTools

Tencent · Released July 2026

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

Facts and pricing

Provider
Tencent
Context window
262K tokens
Input price
1.5 credits / 1M tokens ($0.14 raw)
Output price
6.4 credits / 1M tokens ($0.58 raw)
Vision (image input)
No
Tool calling
Yes
Extended reasoning
No

Credits are what Zeplik bills: 1 credit = $0.10, computed from the raw provider rate with a 1.10x margin. Raw prices shown per 1M tokens.

Try Hy3 now

Ask Hy3 anything. Your prompt opens in the Zeplik app with this model selected.

Hy3

What Hy3 is best for

Tencent family

ModelContextInput cr/MOutput cr/MReleased
Hy3 (free)262K00July 2026
Hy3262K1.56.4July 2026
Hy3 preview262K0.692.3April 2026
Hunyuan A13B Instruct131K1.56.3July 2025

Frequently asked questions

What is Hy3?
Hy3 is an AI model by Tencent. Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
How much does Hy3 cost on Zeplik?
Input tokens cost 1.5 credits per million and output tokens 6.4 credits per million (1 credit = $0.10; the raw provider rates are $0.14 and $0.58 per million). New accounts start with free credits.
How long can a conversation with Hy3 be?
Hy3 has a 262K-token context window (262,144 tokens), which covers the conversation plus any documents you attach.
Does Hy3 support images and tools?
Hy3 is text-only and supports tool calling.

Related models

Hy3 (free)General purpose

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

262K ctx0 cr/M outJuly 2026
Hy3 previewGeneral purpose

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

262K ctx2.3 cr/M outApril 2026
Hunyuan A13B InstructGeneral purpose

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark...

131K ctx6.3 cr/M outJuly 2025
GPT-5.6 Luna ProFrontier

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 LunaFrontier

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

1.1M ctx66.0 cr/M outJuly 2026
GPT-5.6 Terra ProFrontier

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. Learn more in OpenAI's docs: https://developers.openai.com/api/docs/guides/reasoning#reasoning-mode

1.1M ctx165 cr/M outJuly 2026
Hy3 - Tencent AI Model | Zeplik Chat