Hy4 preview
Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.
Model by Tencent
Install
Pick your client. Read the repository before you give any tool access to your data.
{
"model": "tencent/hy4-preview",
"baseURL": "https://openrouter.ai/api/v1"
}OpenAI-compatible API: point any OpenAI SDK at the base URL and use this model id.
Settings it needs
OPENROUTER_API_KEYrequiredsecret
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: code-generation, agent-orchestration
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Price and limits
| Variant | Input $/M tokens | Output $/M tokens | Cached input $/M |
|---|---|---|---|
| Standard | $0.834 | $2.5 | $0.042 |
Price as of Oct 26, 2026 from OpenRouter. Prices change often; check before you rely on one.
- Provider
- Tencent
- Model id
tencent/hy4-preview- Context window
- 1,048,576 tokens (1M)
- Max output
- 64,000 tokens
- Input
- text
- Output
- text
- Tool calling
- Yes
- Structured outputs
- Yes
- Reasoning
- Yes
- Weights
- Open: tencent/Hy4-preview
- Released
- Aug 28, 2026
Price changes
- Oct 26, 2026: $0.834 in / $2.5 out
- Oct 24, 2026: $0.751 in / $2.25 out
Details
- Auth
- API key
- License
- License unknown
- Website
- hunyuan.tencent.com
- First seen
- Oct 24, 2026
- Last checked
- Oct 26, 2026
- Source
- OpenRouter
More from Tencent
- 0.855score
aig-scanner
TencentOfficial
A.I.G Scanner — AI security scanning for infrastructure, AI tools / skills, AI Agents, and LLM jailbreak evaluation via Tencent Zhuque Lab AI-Infra-Guard.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
indirect-injection-detection
TencentOfficial
Detect indirect prompt injection (goal hijack).
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
memory-rag-poisoning-detection
TencentOfficial
Detect persistent-memory poisoning and RAG/knowledge-base contamination via dialogue testing.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
web-exfiltration-detection
TencentOfficial
Detect data exfiltration via URL path encoding and chained web_fetch navigation.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
tool-abuse-detection
TencentOfficial
Detect tool misuse and unexpected code execution via dialogue testing.
SkillAFreshness: A★ 7.1KClaude Code +9 - 0.849score
authorization-bypass-detection
TencentOfficial
Detect privilege escalation and unauthorized access via dialogue.
SkillAFreshness: A★ 7.1KClaude Code +9
Cite this page
Hy4 preview: price, context window, tool use. Agent Mart. https://agentmart.dev/models/tencent-hy4-preview (last updated 2026-10-26)