AI model comparison

Hy4 vs Particle-1

Side by side comparison of Hy4 and Particle-1 on pricing, benchmark scores, context window, and more.

The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity

Input / 1M
$0.42
Output / 1M
$1.25
Context
1.05M

Particle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash.

Input / 1M
$0.07
Output / 1M
$0.50
Context
1.05M

Comparing image generators? Compare image models

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

particle-ai logo

Particle-1

3.7x cheaper for a typical chat

Higher intelligence score

Not available

Not enough benchmark data

Larger context window

Tie

1.05M vs 1.05M tokens

Newer release

tencent logo

Hy4

Released November 4, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

tencent logoHy434.6
particle-ai logoParticle-1Not available

Coding index

tencent logoHy4Not available
particle-ai logoParticle-1Not available

Agentic index

tencent logoHy4Not available
particle-ai logoParticle-1Not available

Pricing

Hy4 vs Particle-1 API pricing

Per-token API rates. Cheaper option highlighted.

Metrictencent logoHy4particle-ai logoParticle-1
Input tokensPer 1M tokens$0.42$0.07
Output tokensPer 1M tokens$1.25$0.50
Cached input (read)Per 1M tokens$0.02$0.03
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

tencent logoHy4$1.46
particle-ai logoParticle-1$0.39

Coding task

30K in, 4K out

tencent logoHy4$17.51$5.63 cached
particle-ai logoParticle-1$4.10$2.90 cached

Long document summary

150K in, 2K out

tencent logoHy4$65.05$5.65 cached
particle-ai logoParticle-1$11.50$5.50 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metrictencent logoHy4particle-ai logoParticle-1
Context window1.05M tokens1.05M tokens
Max output66K tokens131K tokens
Input typesImage, TextImage, Text
Output typesTextText
Reasoning effort levelsHigh, Low, NoneMax, Extra high, High, Medium, Low, Minimal, None
Default reasoning effortHighHigh
Release dateNovember 4, 2026October 28, 2026

Features

Supported features

API features available for each model.

Metrictencent logoHy4particle-ai logoParticle-1
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

Particle-1 is 3.7x cheaper for a typical chat. The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is Hy4 or Particle-1 cheaper?

Particle-1 is cheaper for a typical chat (2K input tokens and 500 output tokens). Particle-1 costs $0.07 per 1M input tokens and $0.50 per 1M output tokens, while Hy4 costs $0.42 per 1M input tokens and $1.25 per 1M output tokens.

Which has a bigger context window, Hy4 or Particle-1?

Hy4 supports up to 1.05M tokens of context, compared with 1.05M for Particle-1.

Can I use Hy4 and Particle-1 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Hy4 and Particle-1 answer side by side and keep the better response.

tencent logoparticle-ai logo

Why choose? Ask both.

Send one prompt to Hy4 and Particle-1 at the same time. Compare the answers side by side and keep the best one.