Skip to content
Alpha
  • Models
  • Rankings
  • Ori

Footer

OpenRouterOpenRouter
© 2026 OpenRouter, Inc

Product

  • Chat
  • Rankings
  • Benchmarks
  • Apps
  • Discover
  • Models
  • Ori
  • Collections
  • Providers
  • Tools
  • Pricing
  • Business
  • EU routing
  • Enterprise
  • Labs

Company

  • About
  • Blog
  • Careers
    Hiring
  • Privacy
  • Terms of Service
  • Trust Center
  • Support
  • Works With OR
  • Data
  • Brand

Developer

  • Documentation
  • API Reference
  • Developer Platform
  • Status
  • AI Site Map

Connect

  • Discord
  • GitHub
  • LinkedIn
  • X
  • YouTube
  1. Home
  2. /
  3. Compare

Perceptron Mk1 vs Hy3 preview

Compare Perceptron Mk1 from perceptron and Hy3 preview from tencent on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the OpenRouter API.

Favicon for perceptron
Perceptron Mk1
Favicon for tencent
Hy3 preview
Favicon for perceptron
Perceptron Mk1
Favicon for tencent
Hy3 preview

Overview

Perceptron Mk1
Author
perceptron
Hy3 preview
Author
tencent
Perceptron Mk1
Context length
33Ktokens
Hy3 preview
Context length
262Ktokens
Perceptron Mk1
Reasoning
Hy3 preview
Reasoning
Perceptron Mk1
Input modalities
Hy3 preview
Input modalities
Perceptron Mk1
Output modalities
Hy3 preview
Output modalities

Perceptron Mk1 vs Hy3 preview: side-by-side summary

Perceptron Mk1 and Hy3 preview are available through the OpenRouter API, so switching between them takes a model slug change rather than a new integration.

Perceptron Mk1, from perceptron, has a 32,768-token context window and is priced at $0.15/M tokens input, $1.50/M tokens output on OpenRouter.

Hy3 preview, from tencent, has a 262,144-token context window and is priced at $0.18/M tokens input, $0.60/M tokens output on OpenRouter.

Context window
  • Perceptron Mk1: 32,768 tokens
  • Hy3 preview: 262,144 tokens
Price
  • Perceptron Mk1: $0.15/M tokens input, $1.50/M tokens output
  • Hy3 preview: $0.18/M tokens input, $0.60/M tokens output
Provided by
  • Perceptron Mk1: perceptron
  • Hy3 preview: tencent
  • Perceptron Mk1 model details, providers and pricing
  • Hy3 preview model details, providers and pricing

Perceptron Mk1 vs Hy3 preview at a glance

Perceptron Mk1 vs Hy3 preview comparison
AttributePerceptron Mk1Hy3 preview
Input price$0.15/M tokens$0.18/M tokens
Output price$1.50/M tokens$0.60/M tokens
Context window32,768 tokens262,144 tokens
Intelligence IndexNot available22.7
Coding IndexNot availableNot available
Agentic IndexNot availableNot available
Latency (p50)2.79 s2.25 s
Throughput (p50)7.0 tok/s92.0 tok/s

Benchmark data updated Oct 5, 2026

Frequently asked questions

Is Perceptron Mk1 cheaper than Hy3 preview?

Perceptron Mk1 and Hy3 preview trade off on price: Perceptron Mk1 costs $0.15/M tokens input and $1.50/M tokens output, while Hy3 preview costs $0.18/M tokens input and $0.60/M tokens output, so Perceptron Mk1 is cheaper for input tokens and Hy3 preview is cheaper for output tokens.

Which has the longer context window, Perceptron Mk1 or Hy3 preview?

Hy3 preview has the longer context window at 262,144 tokens, compared with 32,768 tokens for Perceptron Mk1.

Which is faster, Perceptron Mk1 or Hy3 preview?

Hy3 preview is faster on OpenRouter, generating a median 92.0 tokens per second compared with 7.0 tokens per second for Perceptron Mk1.