tencent/hy4-20261104
The official release of Hy4 delivers comprehensive and substantial improvements over Hy4 Preview, with particularly strong gains in agentic capabilities and performance across a wide range of long-horizon, real-world productivity tasks. It also introduces visual understanding for
- Context window
- 1,048,576
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, promptCaching, reasoning, structuredOutputs, toolCalling, visionInput
Benchmarks
- Artificial Analysis: 34.6
- OpenRouter Benchmarks: 83.165%
Inference prices
- Published price : $0.02 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.42 / input_tokens_per_million · openRouter ↗
- Published price : $1.25 / output_tokens_per_million · openRouter ↗
tencent/hy3-preview-20260421
Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to balance speed and depth depending on the task, while delivering
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, toolCalling
Benchmarks
- Artificial Analysis: 25.3
- LMArena: 1,401.297
- OpenCompass LLM: 81%
Inference prices
- Published price : $0.06 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.18 / input_tokens_per_million · openRouter ↗
- Published price : $0.60 / output_tokens_per_million · openRouter ↗
cheaperInference/hy3
- Context window
- 262,144
- Maximum output
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs, toolCalling
Inference prices
cheaperInference/hy4-preview
- Context window
- 1,048,576
- Maximum output
- 64,000
- Input modalities
- text, image
- Output modalities
- text
- Capabilities
- multimodal, reasoning, structuredOutputs, toolCalling, visionInput
Inference prices
cheaperInference/hy-mt2-lite
- Context window
- 8,000
- Maximum output
- 4,000
- Input modalities
- text
- Output modalities
- text
Inference prices
cheaperInference/hy-mt2-plus
- Context window
- 8,000
- Maximum output
- 4,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Inference prices
cheaperInference/hy-mt2-pro
- Context window
- 8,000
- Maximum output
- 4,000
- Input modalities
- text
- Output modalities
- text
- Capabilities
- structuredOutputs
Inference prices
vertexAI/publishers/hf-tencent/models/drive-rl@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-tencent/models/drive-sft@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-tencent/models/hunyuan-0.5b-instruct@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-tencent/models/hunyuan-1.8b-instruct@001
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-tencent/models/hunyuan-7b-instruct-awq-int4@001
- Input modalities
- text
- Output modalities
- text
tencent/hunyuan-a13b-instruct
Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thought. It offers competitive benchmark performance across mathematics, science, coding, and multi-turn
- Context window
- 131,072
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs
Benchmarks
Inference prices
- Published price : $0.14 / input_tokens_per_million · openRouter ↗
- Published price : $0.57 / output_tokens_per_million · openRouter ↗
siliconFlow/tencent/Hunyuan-MT-7B
The Hunyuan Translation Model consists of a translation model, Hunyuan-MT-7B, and an ensemble model, Hunyuan-MT-Chimera. Hunyuan-MT-7B is a lightweight translation model with 7 billion parameters used to translate source text into the target language. The model supports mutual tr
- Maximum output
- 32,768
- Input modalities
- text
- Output modalities
- text
- Capabilities
- reasoning, structuredOutputs
huggingface/tencent/HunyuanOCR
- Capabilities
- multimodal, visionInput
tencent/hy3-20260706
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: a direct no-think mode by default, plus low and high chai
- Context window
- 262,144
- Input modalities
- text
- Output modalities
- text
- Capabilities
- promptCaching, reasoning, structuredOutputs, toolCalling
Inference prices
- Published price : $0.02 / cache_read_tokens_per_million · openRouter ↗
- Published price : $0.08 / input_tokens_per_million · openRouter ↗
- Published price : $0.33 / output_tokens_per_million · openRouter ↗
vertexAI/publishers/tencent/models/tencent-hy3@hy3-fp8
- Input modalities
- text
- Output modalities
- text
vertexAI/publishers/hf-tencent/models/hy3-fp8@001
- Input modalities
- text
- Output modalities
- text