Skip to content
ElastixAI
All models

Tencent

Text in, Text out

Hy4-Preview

hy4
Talk to us

Tencent's 770B-parameter mixture-of-experts model for coding, office work and agentic workflows, with 49B active per token: the top 8 of 256 routed experts plus a shared expert. Text in, with a context window of about a million tokens.

Context window
1M tokens
Precision
4 bits
Price per 1M tokens
$2.23 out · $0.08 in · $0.06 cached
Integration
OpenAI-compatible API
ReasoningMoEAgentic coding

Playground

Hy4-Preview

Coming soon

Hy4-Preview is coming soon

We’re bringing it up on a processor built for it. Talk to us for early access.

Talk to us

Use it in your app

API documentation

Client Libraries

curl https://api.elastix.ai/v1/chat/completions \
  -H "Authorization: Bearer $ELASTIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'