Tencent

Hy3

Released 2026-07-06

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:...

You send / 1M

$0.132

tokens in

It replies / 1M

$0.528

tokens out

Memory

262K

tokens it can read at once

Typical request

$0.0004

1,000 words in, 400 out

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
Tencent · fp8$0.132$0.528100%Read
Novita$0.140$0.580100%Read
Phala$0.150$0.640100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text
  • Writes: text
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 128K tokens
  • Repeated text is billed at $0.033 per 1M (prompt caching)

Similar models

Appears in

Estimate your monthly cost with Hy3 →