All Models

Hy3 (NovitaAI)

Hy Reasoning Tool Calling Open Weights Structured Output

Tencent Hy reasoning model for coding, instruction following, and agent tasks

Providers 1
Released Jul 6, 2026
Input Modalities text
Output Modalities text
Tarsk Use coding

Benchmarks

42.2
Intelligence Index
58.8
Coding Index

Available Providers (1)

Provider Model ID Input Cost Output Cost Context Max Output Docs
LLM Gateway novita/hy3 $0.14/MTok $0.58/MTok 262.1K 262.1K

Capabilities

Reasoning
Tool Calling
Attachments
Open Weights
Structured Output