Models and providers
1. How your content travels
Beemm Vision is an orchestration platform. It does not train, host or operate artificial intelligence models: it routes your request to the model you select. Concretely, your prompt and any file you attach travel from Beemm Vision to a gateway, and from that gateway to the editor of the model.
This page identifies, for every model made available, the gateway used and the company that edits the model. It is the annex referred to in article 12 of the Terms of Sale and in section 7 of the Privacy Policy.
Last verified against the production model registry: 9 August 2026.
2. The gateways
| Gateway | Role | Location |
|---|---|---|
| FAL — fal.ai | Default gateway for every image and video model, and for the image editing operations | United States — Standard Contractual Clauses |
| KIE — kie.ai | Alternative gateway, currently used for Nano Banana Pro only | Outside the European Union — Standard Contractual Clauses |
| OpenRouter — openrouter.ai | Gateway for every language model: the assistant, and the text and vision nodes of the workflows | United States — Standard Contractual Clauses |
The choice of gateway is ours and may change for technical or tariff reasons. The choice of model editor is yours: it follows from the model you select.
3. Image and video models
| Model editor | Models | Type | Routed through |
|---|---|---|---|
| Nano Banana Pro, Nano Banana 2, Nano Banana Lite, Veo 3.1 Fast, Gemini Omni Flash | Image, video | FAL — Nano Banana Pro may also be routed through KIE | |
| ByteDance | Seedream 4.5 and 5 (Lite, Pro), Seedance 1.5 Pro, Seedance 2.0 (Fast, Mini, reference-to-video) | Image, video | FAL |
| Alibaba | Qwen Image Max, Qwen Image 2 (and Pro), Wan 2.6 Flash, Wan 2.7 | Image, video | FAL |
| Kuaishou | Kling Image v3, Kling O3, Kling Video v3 | Image, video | FAL |
| OpenAI | GPT Image 1.5, GPT Image 2 (generation and editing) | Image | FAL |
| xAI | Grok Imagine Image, Grok Imagine Video | Image, video | FAL |
| Tencent | Hunyuan Image v3 | Image | FAL |
| Black Forest Labs | FLUX 2 Pro (generation and editing) | Image | FAL |
| Luma AI | Uni-1, Uni-1 Max | Image | FAL |
| Recraft | Recraft v4 Vector, Recraft v4.1 Pro, Recraft v4.1 Pro Vector | Image, vector | FAL |
| Ideogram | Ideogram v4 | Image | FAL |
| Lightricks | LTX 2.3, LTX 2.3 Fast, LTX Reframe | Video | FAL |
| HiDream.ai | HiDream O1 | Image | FAL |
4. Image editing operations
Upscaling, background removal, object erasing, inpainting and outpainting also call third-party models:
| Model editor | Models | Type | Routed through |
|---|---|---|---|
| Topaz Labs | Topaz Upscale | Upscaling | FAL |
| Bria AI | Eraser, Expand, Generative Fill | Object removal, outpainting, inpainting | FAL |
| Black Forest Labs | FLUX Fill | Inpainting | FAL |
| Open-source models hosted by FAL | BiRefNet v2, Clarity Upscaler | Background removal, upscaling | FAL |
5. Language models
The assistant and the text nodes of the workflows call language models through OpenRouter. Several of their editors are established outside the European Union, including in China (DeepSeek, Alibaba, Moonshot AI, Z.ai, MiniMax). The corresponding transfers are governed by Standard Contractual Clauses.
| Model editor | Models | Type | Routed through |
|---|---|---|---|
| Anthropic | Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5 | Text | OpenRouter |
| Gemini 3.1 Pro, Gemini 3 Flash, Gemini 3.1 Flash Lite, Gemini 3.5 and 3.6 Flash, Gemini 2.5 Flash | Text, vision | OpenRouter | |
| OpenAI | GPT-4o | Text, vision | OpenRouter |
| DeepSeek | DeepSeek V4 Flash, V4 Pro, V3 | Text | OpenRouter |
| Alibaba | Qwen 3 (32B, 72B), Qwen 2.5 72B, Qwen 3 VL | Text, vision | OpenRouter |
| Moonshot AI | Kimi K3 | Text | OpenRouter |
| Z.ai | GLM 5.2 | Text | OpenRouter |
| MiniMax | MiniMax M3, M2.7 | Text | OpenRouter |
| xAI | Grok 4 Fast | Text | OpenRouter |
6. Browser extension analysis
The official Beemm Vision Chrome extension may observe image eligibility locally on ordinary HTTP(S) pages so a Prompt control can appear. No image data is sent on hover. After an explicit action and confirmation, the extension sends the selected image or screen region to a vision language model that you choose in the extension (default: Google Gemini 2.5 Flash). That request is routed through the FAL gateway (OpenRouter vision route). A temporary copy may exist on our servers for the duration of the analysis and is deleted afterwards. Credit ledger entries and security logs remain.
| Model editor | Models | Type | Routed through |
|---|---|---|---|
| Google / OpenAI / others (user-selected) | Gemini 2.5 Flash (default) and other catalogued vision models for extension reverse-prompting | Vision → text | FAL (OpenRouter vision) |
7. Training on your content
Beemm does not train any model on your content and does not transfer your content to any third party for that purpose.
Whether a given editor uses the content it receives to train its own models is governed by that editor's own terms, over which we have no control. We configure our integrations so as to request, wherever the gateway or the editor offers the option, that transmitted content not be used for training. We cannot warrant that every editor abstains from doing so, and we will not claim otherwise.
Where this point is decisive for your use case, contact us before using a given model at [email protected] and we will tell you what we know of that editor's position, and what we do not.
8. Keeping this page accurate
This page is derived from the model registry actually deployed in production, and is updated whenever a model is added or withdrawn. The date of the last verification appears in section 1. If you notice a discrepancy between this page and what the interface offers, tell us at [email protected] — an out-of-date annex is a defect we want to know about.