OpenRouter
Catalog quote- Input
- $0.132
- Output
- $0.528
- Cached input
- $0.033
tencentListed Jul 2, 2026
Tencent: Hy3
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:...
Context window262.1K
Max output128K
Provider endpoints8
Benchmark results0
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Access & cost
10 quotesPrices across providers
Your token mix
USD · listed token ratesfeatherless-ai
via Hugging Face- Input
- —
- Output
- —
deepinfra
via Hugging Face- Input
- $0.13
- Output
- $0.53
Tencent
via OpenRoutertencent/fp8 · quantization=fp8 · Base rate; UTC schedule applies
Conditional rate- Input
- $0.0825
- Output
- $0.33
- Cached input
- $0.0206
Tencent
via OpenRoutertencent/fp8 · quantization=fp8 · 00:00–16:00 UTC · rate option 1
Conditional rate- Input
- $0.132
- Output
- $0.528
- Cached input
- $0.033
A rate applies when all its listed conditions match. Dates and times use UTC.
Tencent
via OpenRoutertencent/fp8 · quantization=fp8 · 16:00–00:00 UTC · rate option 2
Conditional rate- Input
- $0.0825
- Output
- $0.33
- Cached input
- $0.0206
A rate applies when all its listed conditions match. Dates and times use UTC.
- Input
- $0.14
- Output
- $0.58
- Cached input
- $0.035
- Input
- $0.14
- Output
- $0.58
- Cached input
- $0.035
- Input
- $0.15
- Output
- $0.64
- Cached input
- $0.04
- Input
- $0.20
- Output
- $0.80
- Cached input
- $0.05
Model specifications
- Developer
- tencent
- Modality
- Language
- Context
- 262,144 tokens
- Maximum output
- 128,000 tokens
- Weights
- Open weights
- Provider listed
- Jul 2, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
tencent/hy3 - huggingface
tencent/Hy3
Sources
Updated Oct 18, 2026
More from tencent
View all ↗tencentListed Aug 27
Hy4-preview
Hy4 preview is a 770B-parameter Mixture-of-Experts flagship model from the Tencent Hy Team, with 49B parameters activated per token and a 1M-token context window. It uses Gated DeepSeek Sparse Attention…
1M contextTool callingStructured outputNo reported score
No reported score
tencentListed Aug 20
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,…
8.2K context1.8BOpen weightsNo reported score
No reported score
$0.044in$0.177out/ 1M tokens · USDTencent · via OpenRouter · 2 endpointstencent/fp8 · quantization=fp8
tencentListed Aug 20
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,…
8.2K context30BStructured outputOpen weightsNo reported score
No reported score
$0.074in$0.295out/ 1M tokens · USDTencent · via OpenRouter · 2 endpointstencent/fp8 · quantization=fp8
tencentListed Aug 19
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,…
8.2K context7BStructured outputOpen weightsNo reported score
No reported score
$0.074in$0.295out/ 1M tokens · USDTencent · via OpenRouter · 2 endpointstencent/fp8 · quantization=fp8