TechCompare LogoTechCompare
Showing centimeters. Press to switch to inches.Showing inches. Press to switch to centimeters.

Tencent Hy API pricing for every model, newest first

By TechCompare · Updated · How we check

A 50,000 token prompt with a 3,000 token answer and half the input cached costs $0.029403 on Hy4, the newest model. Hy3, the lowest cost model Tencent sells itself, runs it for $0.005709.

Every Tencent Hy model and its API price

Newest first. Prices are per 1M tokens. One request is 50K tokens in and 3K out, with 50% of the input cached.

ModelInputOutputCachedContextOne requestListed
Hy4Tencent$0.834$2.501$0.0421.05M$0.0294Nov 4, 2026
Hy4 previewTencent$0.834$2.501$0.0421.05M$0.0294Aug 28, 2026
Hy-MT2-1.8BTencent$0.044$0.177$0.0448K$0.0027Aug 20, 2026
Hy-MT2-30B-A3BTencent$0.074$0.295$0.0748K$0.0046Aug 20, 2026
Hy-MT2-7BTencent$0.074$0.295$0.0748K$0.0046Aug 19, 2026
Hy3Tencent$0.132$0.528$0.033262K$0.0057Jul 6, 2026
Hy3 previewCheapest host: GMICloud$0.18$0.60$0.06262K$0.0078Apr 22, 2026
Hunyuan A13B InstructCheapest host: SiliconFlowLeaves Nov 15, 2026$0.14$0.57$0.14131K$0.0087Jul 8, 2025

Listed is the day OpenRouter added the model. Prices checked Nov 14, 2026.

Hy is Tencent's model family, sold through Tencent Cloud. Older releases carry the full Hunyuan name, like Hunyuan A13B in the table. This page lists all 8 Tencent models OpenRouter carries, newest first, at Tencent's own price where Tencent sells the model and the host that charges least where it doesn't.

Hy4 is the fourth generation general model, at $0.834 input and $2.501 output per million tokens. Hy3 is a 295B mixture of experts model with 21B active and reasoning you can turn up or down, at $0.132 and $0.528.

Newest
Hy4
$0.834 in, $2.501 out per 1M
Lowest cost per request
Hy3
$0.0057 for the request in the table
Largest context
Hy4
1.05M tokens

Calculator

Cost Comparison

Based on 50,000 input tokens (50% cached), 3,000 output tokens, and 100 requests.Prices come live from OpenRouter at each maker's own price where it's listed. Temporary deals are left out.

Loading model prices
Same 50,000 in / 3,000 out (50% cached) scenario, pre-loaded. Adjust tokens, caching, or swap models.
Edit in the full tool

How to read the Tencent Hy prices

Rows show list prices, before any deal, per million tokens. Tencent is running a 50% discount on Hy4 right now, which brings it to $0.417 input and $1.2505 output per million. The table shows list prices, so the deal comes off those. Check the end date before you plan around it. Hy3 has off-peak rates, at $0.0825 input and $0.33 output per million, 38% off input. Tencent Cloud lists the hours, so batch work can move into them.

Hy-MT2 is a separate line built only for translation. It comes in 1.8B, 7B and 30B-A3B sizes, covers 33 language pairs plus 5 pairs for Chinese dialects and minority languages, and can follow a glossary or a style guide. Hy-MT2-7B costs $0.074 input and $0.295 output per million, and its window is 8K tokens, so send long documents a section at a time.

A cached token on Hy4 costs $0.042 per million, 95% off the normal input rate. Hy4 reads up to 1.05M tokens, the largest window in the family.

Verdict

Start with Hy4 and run Hy3, the lowest cost model Tencent sells for the example request, on the same prompts. Use it wherever it passes your checks. For translation, test a Hy-MT2 model before a general one, since that's the only job it was built for.

Deals and off-peak hours change the bill a lot here, so check both on Tencent Cloud before you set a budget.

More LLM pricing scenarios

Claude API Pricing
Every Claude model from Haiku to Fable in one table, with cache and batch prices and what one request costs.
View details
DeepSeek API Pricing
Every DeepSeek model in one table, with cache hit prices, off-peak hours and what one request costs.
View details
Gemini API Pricing
Every Gemini and Gemma model on Google's API in one table, with cached prices, deals and what one request costs.
View details

Related guides

LLM pricing calculator
Put any Hy model next to models from other makers.
View guide
Token counter
Measure your prompts before you price them.
View guide
Tencent Hunyuan
Check deals, off-peak hours and region prices at the source.
View guide

Frequently asked questions

How much does the Tencent Hy API cost?
Hy4 lists $0.834 input and $2.501 output per million tokens, and Hy3 is $0.132 and $0.528. A deal running now brings Hy4 to $0.417 input and $1.2505 output.
Is Hy the same as Hunyuan?
Yes, it's the same Tencent model line. The newer releases go by Hy, and some older ones in the table still carry the Hunyuan name.
What is Hy-MT2?
Tencent's translation models, in 1.8B, 7B and 30B-A3B sizes. They cover 33 language pairs plus 5 pairs for Chinese dialects and minority languages, and can follow a glossary or a style guide. Hy-MT2-7B costs $0.074 input and $0.295 output per million, with an 8K window.
Does Tencent Hy have off-peak pricing?
On some models. Hy3 costs $0.0825 input and $0.33 output per million in off-peak hours. Tencent Cloud lists the hours.
Which Tencent model has the largest context window?
Hy4, the newest, has the largest window at 1.05M tokens.
Where do these prices come from?
From OpenRouter's model list, which we check on a regular schedule. A row shows Tencent's own list price where Tencent sells the model, and the host that charges least where it doesn't. Deals come off the list price.

Related tools

LLM VRAM Calculator

Calculate the VRAM needed to run or fine-tune any LLM at any quantization.

Use tool

Power Cost Estimator

Estimate annual electricity costs for your PC, Server, or TV.

Use tool

Data Transfer Calculator

Estimate transfer times for files over USB, WiFi, Ethernet, and more.

Use tool

JSON Formatter

Validate, format, and minify JSON. Browse it as a tree, run JSONPath queries, compare two documents, or validate against a JSON Schema.

Use tool