AI Rate Card

Hy3 · deepinfra

Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. Today, we introduce Hy3, which outperforms similar-size models and rivals flagship open-source models with 2-5x parameters. It also shows significant gains in utility across various products and productivity tasks.

Base modelAll models on this baseAll models of the providerto the provider

Input, $/1M $0.13

Output, $/1M $0.53

Limits

  • Every plan: 200 requests at once

Last checked 04.11.2026 12:08:11 UTC Source

Context 262 144

Accepts text

Last checked 04.11.2026 12:00:14 UTC

Source —

Price alerts

Sign in to follow the price

API

This model type has no common request format: see the provider's documentation.

Provider's API documentation

Source: AI Rate Card, https://airatecard.com/en/c/offer%3Adeepinfra%7Ctencent/Hy3, prices checked 2026-11-04

Technical details

ID: offer:deepinfra|tencent/Hy3