Hy4 is Tencent's language model with a 1.0M context window and up to 66K output tokens, available from 5 providers, starting at $0.417 / 1M input and $1.25 / 1M output. A large language model from Tencent's Hunyuan series with agentic capabilities, reasoning, tool-use, vision, and structured output support.
Specifications
Canonical IDtencent-hy-4
TypeLanguage
StatusActive
CreatorTencentTencent
Providers
Context Window1.0M tokens
Max Output66K tokens
Input ModalitiesImageText
Output ModalitiesText
Reasoning Effortsdefault
Parameters774B
HuggingFace Likes53
HuggingFace Downloads (30d)2
HuggingFace Downloads (all-time)2
Release Date · 19 days ago
Benchmarks
Intelligence Index
#27
Time to First Token
#532
Output TPS
#146

Capabilities

Input2/5
Text✓
Image✓
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities5/13
Reasoning✓
Adaptive Reasoning·
Function Calling✓
Parallel Function Calling·
Structured Outputs✓
Native JSON Schema✓
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching✓
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
GMI Cloud logo
GMI Cloud
gmi/tencent/hy4
$0.417$1.25$0.021
OpenRouter logo
OpenRouter
tencent/hy4
$0.417$1.25$0.021
Tencent logo
Tencent
tencent/hy4
$0.417$1.25$0.021
Together AI logo
Together AI
together_ai/tencent/Hy4
$0.834$2.50$0.042
$0.417$1.25$0.021

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host Hy4, ranked by cheapest on-demand price. The model needs about 1859 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
p6-b300.48xlargeAWS8× B3002149 GB$142.42/hr

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Hy4 Flash1.0M$0.035$0.141Available
Hy41.0M$0.417$1.25Current
Hy4 Preview1.0M$0.417$1.25Available
Hy 3262K$0.140$0.580Available

Model IDs

gmi/tencent/hy4
tencent-hy-4
tencent-hy4
tencent/hy4
tencent/Hy4
together_ai/tencent/Hy4