Compare AI Models

Select two models to compare their pricing, performance benchmarks, capabilities, and technical specifications side by side.

Model 1

Model 2

Tencent: Hy3

tencent

Select a model

Input Price

Cost per 1M input tokens

$0.14/M tokens

—

Output Price

Cost per 1M output tokens

$0.58/M tokens

—

Cache Read Price

Cost per 1M cached tokens

$0.04/M tokens

—

Context Window

Maximum tokens the model can process

202,752 tokens

—

Max Output Tokens

Maximum tokens in model response

131,072 tokens

—

Input Modalities

Supported input types

text

—

Output Modalities

Supported output types

text

—

SciCode

Scientific computing & algorithms

41.2%

—

TerminalBench Hard

CLI & terminal command generation

34.1%

—

Long Context Reasoning

Understanding large codebases

54.7%

—

IFBench

Instruction following accuracy

63.1%

—

Output Speed

Median tokens per second

178.0 tok/s

—

Function Calling

Can call external functions/APIs

✓ Supported

—

Tool Choice

Control over function selection

✓ Supported

—

Structured Outputs

JSON schema validation

✗ Not supported

—

Reasoning Tokens

Extended thinking for complex problems

✗ Not supported

—

Content Moderation

Content filtering status

Disabled

—

Model ID

tencent/hy3

—

Tokenizer

Other

—

Release Date

Apr 23, 2026

—

Created On OpenRouter

Jul 6, 2026

—

Compare AI Models

Pricing

Context & Modalities

Performance Benchmarks

Capabilities & Features

Technical Details