Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.20 |
| Output tokens | $0.20 |
Capabilities
VisionMultimodalReasoningFunction CallingTool UseJSON ModeCode Execution
About Japanese Stable VLM
The Japanese Stable VLM by Stability AI is a vision-language model that specializes in generating Japanese descriptions for images and providing answers to related questions. It employs an auto-regressive architecture and is trained on a variety of public datasets, excelling in tasks such as image captioning and visual question answering. Tailored for following instructions and producing responses in Japanese that mimic human communication, this model is available for commercial use, distinguishing it from some of Stability AI's earlier models. Users are advised to consider the potential biases and limitations due to the training data.
Model Specs
Released2023-04-10
ArchitectureDecoder Only