Runs onThe places the vendor's own pages say the product runs: your machine, a container environment you run, or a cloud service the vendor runs. It is not a limit.
Models runWhere the vendor's own pages say the product's models run, not a limit: your machine, a container environment you run, the model company's cloud (servers of the company that makes or serves the model), or a cloud provider's model service. For a cloud, read the data and compliance lines of the company running it, linked by its name.
Several providers in one sessionOne session can use models from different providers, for example one agent on one maker's model and another on a second maker's. Switching the single model for the whole session does not count on its own. A tool that is itself a gateway or library routing to the providers its page names counts.
Same role (chat front end) at the same layer (Coding agents and assistants). Up to 4 others, in alphabetical order; nothing is ranked.
Product
Several providersOne session can use models from different providers, for example one agent on one maker's model and another on a second maker's. Switching the single model for the whole session does not count on its own. A tool that is itself a gateway or library routing to the providers its page names counts.
Several endpointsThe tool itself can hold more than one provider or address, so nothing has to sit in front of it to reach different providers.
Model on your machineThe tool can use a model running on your own computer, for example through Ollama, LM Studio, oMLX or llama.cpp.
Local and cloudA local model (on your machine or in a container environment you run) and a cloud model (in its model company's cloud or a cloud provider's model service) can both be used in the same session or setup.
Words in the cells: YesA page we read says so., PartlyA page says part of it, for example separate models per agent without saying the providers can differ., Via a proxyOnly with a proxy, or a local server that imitates a cloud provider's interface, in front of the tool., NoA page we read says the product does not support it., ClaimedA vendor page says so on a marketing or overview page, and we found no guide showing how to set it up., Not foundWe read pages for it and found nothing there. It says nothing about whether the product has the feature., n/aThe question does not apply to the product, for example because it is a model server and not a tool that connects to models., BlankNothing is published for it yet.
Data and compliance
Compliance: Set by whoever runs itThe answer belongs to whoever runs the software, because open-source software has no maker running it for you., for their own deployment.
Data: Set by whoever runs itThe answer belongs to whoever runs the software, because open-source software has no maker running it for you., with telemetry not checked yetWe have not read a page of the right kind for this question yet..
Model and where it runs: Run by its operator.
Details: What the project's own pages state, not a compliance determination.
What the maker's own pages said on the dates shown, not a compliance determination.
GitHub page: open-webui(the product's own site, from our list of products; not read for these lines)
The readings behind this page
Our summary of the vendor's pages as of the dates shown on each line (2026-10-20 to 2026-10-24); confirm on the vendor's page.
One sentence naming both a local and a cloud path
Open WebUI's home page says it can connect to Anthropic, OpenAI, Ollama or any service compatible with those, and that it can run on your own machine, in the cloud, or both. (openwebui.com page, read 2026-10-20)
Models from different providers in one session
In a Multi-Model Chat, the customer's prompt is sent simultaneously to two or more models that were selected. (docs.openwebui.com page, read 2026-10-21)
What a local model must meet
Open WebUI's Ollama guide says Native function calling puts tool schemas into the prompt, so with 2048 tokens of context the model can run short of room and return an empty reply or unprocessed tool-call JSON instead of calling the tool. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's agentic search page says its agentic web search depends on a model with reliable tool calling. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's agentic search page says unlocking its agentic web search features needs native tool calling in the model, plus reasonable multi-step reasoning. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's Ollama guide says switching on the num_ctx control fills in 2048, a very small figure, so a model is easily capped at 2048 tokens, even once OLLAMA_CONTEXT_LENGTH has been raised on the Ollama side. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's Ollama guide says that from Ollama v0.15.5 the default context length is picked from available VRAM: 4096 under 24 GiB, 32768 for 24 up to 48 GiB, and 262144 for 48 GiB or more. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's agentic search page names three local models, Qwen 3.6 27B, Muse Glimmer 30B and Gemma 4 31B, that clear its minimum bar for agentic search, each verified at the time of writing. (docs.openwebui.com page, read 2026-10-23)
Plan, policy and billing
Open WebUI's features page lists restricting model access to chosen users or groups. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's settings page says Admin Settings govern the whole instance, covering API connections, toggles for features, security policies and default behaviors. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's settings page says users cannot turn on for themselves a feature that an admin has disabled globally. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's settings page says that when an admin has turned on Direct Connections, a user can add personal API keys under User Settings, then Connections. (docs.openwebui.com page, read 2026-10-23)
A separate model for planning and for doing
Open WebUI's task models page says its Tasks settings hold two model pickers for background work, both defaulting to the chat's own model. (docs.openwebui.com page, read 2026-10-23)
Open WebUI's task models page says context compaction has its own model picker, which defaults to the current model. (docs.openwebui.com page, read 2026-10-23)
About the product
Open WebUI's README describes Open WebUI as a self-hosted AI platform designed to run entirely offline. (github.com page, read 2026-10-24)
Our reading of vendors' pages, as of the dates shown. Confirm on the vendor's page before relying on any line that cites it. To report an error write to report@crinaro.ai