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.
Local and cloud togetherA 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.
Use a local model: How to set it up(zed.dev page, read 2026-10-22) Settings the guide names: language_models, ollama, api_url, available_models, auto_discover.
Use a local and a cloud model together: How to set it up(zed.dev page, read 2026-10-22) Settings the guide names: language_models, available_models.
Same role (harness / agent client) 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: zed(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 (2026-10-19 to 2026-10-24); confirm on the vendor's page.
Local models
Zed's local-model page lists Ollama, llama.cpp, LM Studio and a local OpenAI-compatible server as local paths for Zed's AI features; its table marks External Agents and Terminal Threads 'Separate config' for each. (zed.dev page, read 2026-10-19)
Cloud models
Zed's API-access page has an OpenAI-compatible endpoint section, for a service the user reaches at their own base URL using a model ID and an API key. (zed.dev page, read 2026-10-19)
Local and cloud models in one session
After providers are configured, the user can switch between their models with the model selector in Zed's message editor. (zed.dev page, read 2026-10-19)
Zed's agent-settings page lists separate model settings for the inline assistant, commit messages, thread summaries, compaction and subagents; for compaction it says to set the compaction model to use a different model than the thread's. (zed.dev page, read 2026-10-19)
What a local model must meet
Zed's Agent Panel page treats a model context window under 80000 tokens as too small for automatic compaction; for such a model it shows a banner over the message editor as the thread nears the token limit. (zed.dev page, read 2026-10-19)
Agentic editing is enabled by the Agent Panel's support for tool calling. (zed.dev page, read 2026-10-19)
Plan, policy and billing
Zed's pricing page says the Personal plan suits users who want an editor with no AI, or who would rather bring their own keys or external agents. (zed.dev page, read 2026-10-23)
Zed's pricing page lists, under its Personal plan, which it marks free, unlimited use with your own API keys or with external agents such as Claude Agent and Codex CLI. (zed.dev page, read 2026-10-23)
Zed's admin controls page says its organization controls leave out third-party extensions, Terminal Threads, External Agents, gateways, local models and bring-your-own-key setups, because these work apart from Zed's servers. (zed.dev page, read 2026-10-23)
Zed's Business overview says the Data & Privacy dashboard is where administrators manage AI and data settings across the organization. (zed.dev page, read 2026-10-23)
Zed's Business overview says members cannot individually override the AI and data settings administrators set for the whole organization. (zed.dev page, read 2026-10-23)
Zed's Use API Access page counts credits bought from a provider, usage-based billing and top-ups as API access, and says that holds when the reader pays the provider directly. (zed.dev page, read 2026-10-19)
Anthropic API credits are separate from Claude Pro and Max subscriptions. (zed.dev page, read 2026-10-19)
A separate model for planning and for doing
Zed allows specific model settings for subagents, thread summaries, Git commit generation, and Inline Assistant. (zed.dev page, read 2026-10-19)
About the product
Zed's README says that on macOS, Linux and Windows the editor can be downloaded directly or installed through a local package manager. (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