Hy3

Built for real-world business scenarios, Hy3 features a 295B/21B active MoE architecture, native 256K context support, and three reasoning modes.

Context
262K
Max output
262K
Input price
$0.14/1M tokens
Output price
$0.58/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming

Details

Model IDtencent/hy3
Provider Novita AI
Creator tencent
Family—
License—
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters—
Architecture—
Context window262K tokens
Max input—
Max output262K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

Chat CompletionsPOST
Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input
$0.14
Output
$0.58
Cache write
—
Cache read
—
Batch in
—
Batch out
—

API

GET/v1/models/novita/tencent/hy3