Hy3

by tencent · family hy3

Facts

Release date	2026-07-06
Retired date	—
Knowledge cutoff	—
Context (max)	262,144
Max output	131,072
Modalities	text → text
Aliases	—
Open weights	yes (tencent/Hy3)
Description	Tencent Hunyuan 295B/21B-active MoE, 256K context, 3.8B MTP layer; default no-think plus low/high CoT modes; agentic/coding focus. GA 2026-07-06; preview shipped 2026-04-24.

Unknown values are shown as —.

Intelligence Index v4.1.1: 42 · base · Source: Artificial Analysis (accessed 2026-08-20)

Offerings

Provider	Wire ID	Endpoint	Protocol	Status	Price (USD / Mtok)	Reasoning
OpenCode Go	`hy3-preview`	go-chat-completions	openai-chat	preview	—	effort · default on · returns reasoning_content
OpenCode Go	`hy3`	go-chat-completions	openai-chat	ga	—	adaptive · default on · returns reasoning_content
OpenRouter	`tencent/hy3`	chat-completions	openai-chat	ga	0.13 / 0.53	effort · default on · returns reasoning_content · round-trips reasoning_content

Reasoning controls

OpenCode Go· hy3-preview· go-chat-completions effort

reasoning_effort nonelowhigh●

effort · default on · returns reasoning_content

OpenCode Go· hy3· go-chat-completions adaptive

adaptive · default on · returns reasoning_content

OpenRouter· tencent/hy3· chat-completions effort

reasoning.effort nonelowhigh●

effort · default on · returns reasoning_content · round-trips reasoning_content

Example requests

OpenCode Go · openai-chat · hy3-preview

curl 'https://opencode.ai/zen/go/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "hy3-preview",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning_effort": "high"
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/go/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "hy3-preview",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning_effort": "high"
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/go/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "hy3-preview",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning_effort": "high"
  }),
})
console.log(await resp.json())

OpenCode Go · openai-chat · hy3

curl 'https://opencode.ai/zen/go/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "hy3",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'

Python (requests)

import requests

resp = requests.post(
    "https://opencode.ai/zen/go/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "hy3",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://opencode.ai/zen/go/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "hy3",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())

OpenRouter · openai-chat · tencent/hy3

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "tencent/hy3",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "high"
  }
}'

Python (requests)

import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "tencent/hy3",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())

TypeScript (fetch)

const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "tencent/hy3",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())

⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).