# SenseNova-Loop-9B

> SenseNova-Loop-9B is SenseTime's open-weight multimodal model that loops 32 decoder layers into 56 executions. It takes text and images, supports a 512K-token context, and targets reasoning and agentic work. Listed as upcoming.

**ID**: `sensenova/sensenova-loop-9b`  
**Creator**: sensenova  
**Category**: text  
**Context**: 524K tokens  
**Status**: Coming soon — announced, not yet routable on AnyRouter; requests return 404 `model_not_yet_available`.  
**Note**: Coming soon. SenseTime released the open weights on 2026-11-17 under Apache 2.0; no inference API serves them yet. We will list prices and route requests once a host does.  
**Pricing**: Not published yet  
**Released**: 2026-11-17  
**Links**: [Weights on Hugging Face](https://huggingface.co/sensenova/SenseNova-Loop-9B) · [Announcement](https://x.com/SenseTime_AI/status/2122702684985938356)  
**Web page**: https://anyrouter.dev/model/sensenova/sensenova-loop-9b

**Input modalities**: text, image  
**Output modalities**: text  

**Capabilities**: chat, function-calling, reasoning
