Multimodal models
Written by
Updated at May 13, 2025
Foundation Models provides access to large vision language models that allow you to generate texts from a text prompt and image. These models are available in batch mode.
To access a model, use the standard model URI: gpt://<folder_ID>/<model_name>/<branch>.
| Model | URI | Context |
|---|---|---|
| Qwen2 VL 7BModel cardApache 2.0 license | gpt://<folder_ID>/qwen2-vl-7b-instruct/ |
4096 |
| Qwen2.5 VL 7BModel cardApache 2.0 license | gpt://<folder_ID>/qwen2.5-vl-7b-instruct/ |
4096 |
| Qwen 2.5 VL 32B InstructModel cardApache 2.0 license | gpt://<folder_ID>/qwen2.5-vl-32b-instruct/ |
4096 |
| DeepSeek 2 VLModel cardDeepSeek license | gpt://<folder_ID>/deepseek-vl2/ |
4096 |
| DeepSeek 2 VL TinyModel cardDeepSeek license | gpt://<folder_ID>/deepseek-vl2-tiny/ |
4096 |
| Gemma3 4B itModel cardGemma Terms of Use | gpt://<folder_ID>/gemma-3-4b-it/ |
4096 |
| Gemma3 12B itModel cardGemma Terms of Use | gpt://<folder_ID>/gemma-3-12b-it/ |
4096 |
| Gemma3 27B itModel cardGemma Terms of Use | gpt://<folder_ID>/gemma-3-27b-it/ |
4096 |