HY-Vision-1.5-Thinking
Tencent deep-thinking vision model for VQA, OCR, charts and visual grounding.
Specs
- Context
- 41K
- Max output
- 24.6K
- Input price
- ¥3/ 1M tokens
- Output price
- ¥9/ 1M tokens
- Released
- 2025-09-16
Context
- Context window
- 41K
- Max input
- 16.4K
- Max output
- 24.6K
Pricing · CNY / 1M tokens
- Input
- ¥3
- Output
- ¥9
- Cache read
- —
- Cache write
- —
Modalities
- Input
- TextImage
- Output
- Text
API
- API types
Reasoning
- Reasoning
- Yes
- Levels
- —
Info
- Status
- Active
- Released
- 2025-09-16
- Knowledge cutoff
- —
Features
- Not published
How to call
1 provider
tencentmodel = hunyuan-t1-vision-20250916
chat
POSThttps://tokenhub.tencentmaas.com/v1/chat/completions
JSON
Standard format
{
"id": "hunyuan-t1-vision-20250916",
"object": "model",
"created": 1757980800,
"owned_by": "tencent",
"name": "HY-Vision-1.5-Thinking",
"api": {
"types": [
"chat"
]
},
"limits": {
"context": 40960,
"input": 16384,
"output": 24576
},
"modalities": {
"input": [
"text",
"image"
],
"output": [
"text"
]
},
"reasoning": {
"supported": true,
"efforts": []
},
"pricing": {
"currency": "CNY",
"unit": "1M_tokens",
"input": 3,
"output": 9,
"cache_read": null,
"cache_write": null
},
"features": [],
"info": {
"status": "active",
"release_date": "2025-09-16",
"knowledge_cutoff": null,
"description": "Tencent deep-thinking vision model for VQA, OCR, charts and visual grounding.",
"docs": "https://cloud.tencent.com/document/product/1823/130051",
"verified_at": "2026-10-10"
}
}Official sources
4