Skip to content

Hy4 vs Hy4 preview

Hy4 (Tencent) and Hy4 preview (Tencent) are listed at different prices. Hy4 costs less: $0.417 per 1M input tokens and $1.251 per 1M output tokens, against $0.751 and $2.251 for Hy4 preview. Both hold 1,048,576 tokens of context. Hy4 can write up to 65,536 tokens in one response, against 64,000 for Hy4 preview. Hy4 accepts text and images and produces text; Hy4 preview accepts text and produces text.

Tencent: Hy4 accepts text and images, while Tencent: Hy4 preview accepts text; both produce text and support tools, structured outputs, response formats and reasoning. Each has a 1,048,576-token context window, with output limits of 65,536 and 64,000 tokens, respectively.

Compared from catalog data checked

Hy4

$0.417 in
$1.251 out
1.05M context

Hy4 preview

$0.751 in
$2.251 out
1.05M context

Side by side

0.00 the better figure in a row
Hy4 and Hy4 preview specifications side by side
SpecificationHy4Hy4 preview
Maker Tencent Tencent
Added to catalog 4 Nov 2026 28 Aug 2026
Input, per 1M tokens $0.417 $0.751
Output, per 1M tokens $1.251 $2.251
Cached input read, per 1M $0.021 $0.0378
Context windowTokens 1,048,576 1,048,576
Max outputTokens 65,536 64,000
Accepts image, text text
Produces text text
Tool calling Yes Yes
Structured outputs Yes Yes
Reasoning effort control Yes Yes

List prices through OpenRouter, in US dollars. Each model's page has its variants, price history and sample outputs.

What the same task costs

List price for one request, from the token counts shown. The same four tasks are priced on every model page.

Check the provider's pageToken counts are estimates, and the two models count tokens differently.
Cost of the same task on Hy4 and Hy4 preview
TaskHy4Hy4 preview
Answer a short question500 in / 300 out $0.0006 $0.0011
Summarise a 50-page PDF25,000 in / 800 out $0.011 $0.021
Review a 2,000-line source file30,000 in / 2,000 out $0.015 $0.027
Read a 300-page contract set150,000 in / 1,500 out $0.064 $0.116

Which to choose

Choose Hy4 if

  • Input tokens cost less: $0.417 against $0.751 per 1M
  • Output tokens cost less: $1.251 against $2.251 per 1M
  • Cached input costs less: $0.021 against $0.0378 per 1M
  • You need longer answers in one response: 65,536 tokens against 64,000
  • It has to read images, which the other model does not
Hy4 details

Choose Hy4 preview if

No row of the table favours Hy4 preview. The difference, if there is one, is in the answers it writes: try it on your own task.

Hy4 preview details

Neither maker's quality claims are repeated here. The reliable test is your own task: ask both the same question and read the two answers.

Comparison questions

Is Hy4 cheaper than Hy4 preview?

Yes, Hy4 is the cheaper of the two. Hy4 costs $0.417 per 1M input tokens and $1.251 per 1M output tokens; Hy4 preview costs $0.751 and $2.251 as checked on 22 Nov 2026.

Which has the larger context window, Hy4 or Hy4 preview?

Neither: both hold 1,048,576 tokens.

Which is better for coding, Hy4 or Hy4 preview?

This page does not rank models on quality, and it does not repeat either maker's claims. The table shows what each accepts, supports and costs; the reliable test is your own task: give both the same piece of code and compare the answers.

Can I use both Hy4 and Hy4 preview?

Neither is offered in the Upend chat today. Both are listed in the catalog through OpenRouter, with the figures shown here.

Find the model for your task.

Every comparison is computed from the live catalog.

Sign in to Upend

Use an account you already have, or get a one-time code by email.

Use a password instead

For accounts that already have a password. Forgotten it? An emailed code signs you in just the same.