| --- |
| pipeline_tag: image-text-to-text |
| license: other |
| license_name: moondream-model-license-1.0 |
| license_link: https://moondream.ai/licenses/model/1.0 |
| tags: |
| - moondream |
| - vision |
| - image-text-to-text |
| - object-detection |
| --- |
| |
| # Moondream 3.1 |
|
|
| Moondream 3.1 is a vision language model with a mixture-of-experts architecture (9B total parameters, 2B active). It delivers state-of-the-art visual reasoning and detection while staying fast and cheap to deploy. Skills include `query`, `detect`, `point`, and `caption`, all native and all returning structured output. |
|
|
| For the full story on what's new — including how we trained it and how it holds up on your own tasks — see the release notes. |
|
|
| [✨ Playground](https://moondream.ai/playground)   ·   [☁️ Cloud API](https://moondream.ai/p/cloud)   ·   [📝 Release notes](https://moondream.ai/blog/moondream-3-1-beyond-benchmarks)   ·   [📄 License](https://moondream.ai/licenses/model/1.0) |
|
|
| ## Run locally with Photon |
|
|
| [Photon](https://moondream.ai/p/photon) is Moondream's high-performance inference engine. It runs the model locally on NVIDIA GPUs (Ampere or newer) and Apple Silicon Macs, with the same API as [Moondream Cloud](https://moondream.ai/p/cloud). |
|
|
| ```bash |
| pip install moondream |
| ``` |
|
|
| ```python |
| import moondream as md |
| from PIL import Image |
| |
| # Runs locally via Photon. Weights download from Hugging Face on first use. |
| model = md.vl(local=True, model="moondream3.1-9B-A2B") |
| |
| image = Image.open("photo.jpg") |
| |
| # Caption |
| print(model.caption(image)["caption"]) |
| |
| # Visual question answering |
| print(model.query(image, "What's in this image?")["answer"]) |
| |
| # Open-vocabulary detection |
| for obj in model.detect(image, "person")["objects"]: |
| print(obj) |
| |
| # Pointing |
| for point in model.point(image, "person")["points"]: |
| print(point) |
| ``` |
|
|
| No API key is required to run the base model locally. (You'll only need one to run finetunes or to call [Moondream Cloud](https://moondream.ai/p/cloud).) For supported hardware, streaming, finetunes, and production serving with Triton, see the [local inference guide](https://docs.moondream.ai/running-locally). |
|
|
| ## Cloud API |
|
|
| Prefer a hosted endpoint? The same skills are available through [Moondream Cloud](https://moondream.ai/p/cloud) with a generous free tier. See the [quickstart](https://docs.moondream.ai/quickstart) to make your first call. |
|
|
| ## License |
|
|
| Moondream 3.1 is released under the [Moondream Model License](https://moondream.ai/licenses/model/1.0). |
|
|
