AI TOOLS RADAR
Submit
All models / TENCENT
tencent logo
tencent

Tencent: Hy3

Source description (English)

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

View source on OpenRouter Hugging Face
Overview

Model specifications

Context
262,144 tokens
Maximum output
128,000 tokens
Architecture
text->text
Tokenizer
Other
Knowledge cutoff
Not provided
Moderated
No
OPENROUTER

Complete pricing

Synchronized OpenRouter rates. Token prices are shown per one million tokens.

Input
$0.132
per 1M tokens
Output
$0.528
per 1M tokens
Cache read
$0.033
per 1M tokens
API

Model configuration

Default parameters

temperature
0.9
top_p
1

Reasoning

Reasoning required
No
Default parameters
high
Capabilities
high, low, none
API

Quick start

Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.

API documentation

curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"tencent/hy3","messages":[{"role":"user","content":"Hello!"}]}'
Capabilities

Input → Output

Input
text
Output
text
Reasoning

Yes · high · low · none

API

Supported API parameters

frequency_penaltyinclude_reasoninglogit_biasmax_completion_tokensmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Available providers

6 providers

Checked: September 23, 2026

Live providers on OpenRouter

Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.

OpenRouter

DeepInfra

fp4
Context
262K
Maximum output
131K
Input
$0.13
Output
$0.53
Cache read
$0.033
Cache write
Not provided

Tencent

fp8
Context
262K
Maximum output
128K
Input
$0.132
Output
$0.528
Cache read
$0.033
Cache write
Not provided

Novita

Not provided
Context
262K
Maximum output
236K
Input
$0.14
Output
$0.58
Cache read
$0.035
Cache write
Not provided

GMICloud

bf16
Context
262K
Maximum output
236K
Input
$0.14
Output
$0.58
Cache read
$0.035
Cache write
Not provided

Phala

Not provided
Context
262K
Maximum output
236K
Input
$0.15
Output
$0.64
Cache read
$0.04
Cache write
Not provided

AtlasCloud

fp8
Context
262K
Maximum output
131K
Input
$0.2
Output
$0.8
Cache read
$0.05
Cache write
Not provided
tencent

4 models

All models
tencent logotencent

Tencent: Hy4 preview

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

Context
1.0M
Input
text
Output
text
Input: $0.834Output: $2.501per 1M tokens
View model details →
tencent logotencent

Tencent: Hy-MT2-1.8B

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided...

Context
8K
Input
text
Output
text
Input: $0.044Output: $0.177per 1M tokens
View model details →
tencent logotencent

Tencent: Hy-MT2-30B-A3B

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and...

Context
8K
Input
text
Output
text
Input: $0.074Output: $0.295per 1M tokens
View model details →
tencent logotencent

Tencent: Hy-MT2-7B

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delimiter-based, contextual, glossary-based, and style-guided translation.

Context
8K
Input
text
Output
text
Input: $0.074Output: $0.295per 1M tokens
View model details →