AiCostCompare

Hy3 preview

by Tencent · tencent/hy3-preview · #121 cheapest of 457 paid models

Prices updated Nov 18, 2026, 4:47 PM UTC · refreshed nightly

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to...

Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol

Pricing

Input

$0.18

per 1M tokens

Output

$0.60

per 1M tokens

Blended (3:1)

$0.285

3 input : 1 output

Cache read

$0.06

per 1M cached tokens

Cache write

—

per 1M tokens

Cache & batch economics

Effective prices for Hy3 preview with prompt caching.

Cache hit rateEffective blended $/1MExample request*vs no cache
0%$0.285$0.019—
50%$0.24$0.013−32%
90%$0.204$0.00816−57%

*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.

What a request costs

WorkloadInput tokensOutput tokensCost / requestCost / 1K requests
Short chat message500300$0.00027$0.27
Document summary8,0001,000$0.00204$2.04
Codebase question (RAG)30,0002,000$0.0066$6.60
Long-context analysis150,0005,000$0.03$30.00

Performance

Intelligence Index

—

AA composite quality

Coding Index

58.8

Math Index

—

Agentic Index

24.1

Output speed

—

median

Time to first token

—

median

Time to first answer

—

after reasoning tokens

Specs

Context window

262K

tokens

Max output

236K

tokens

Input modalities

text

Tokenizer

Other