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.
Several endpoints built inThe tool itself can hold more than one provider or address, so nothing has to sit in front of it to reach different providers.
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 and a cloud model together: How to set it up(github.com page, read 2026-10-23) Settings the guide names: gemini gemma setup, settings.json.
Compared with similar tools
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: gemini-cli(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 2026-10-23); confirm on the vendor's page.
Local models
Gemini CLI's configuration reference lists an experimental Gemma model router, off by default, that needs a local endpoint serving Gemma. (github.com page, read 2026-10-19)
Cloud models
Gemini CLI's readme describes it as an open-source terminal agent for Gemini and lists three ways to authenticate: a Google account sign-in, a Gemini API key and Vertex AI. (github.com page, read 2026-10-19)
Models from different providers in one session
Under agents.overrides in settings.json, Gemini CLI lets you force a specific model and raise the turn limit for a built-in subagent, per the page's example. (github.com page, read 2026-10-21)
Local and cloud in one session
Gemini CLI's model routing page says that its local routing mode, marked experimental, once configured has a locally running Gemma model make the routing decisions in place of a hosted model. (github.com page, read 2026-10-23)
Gemini CLI's model routing page lists, as an experimental option, that with the Gemma local model router enabled in settings.json the CLI uses the local Gemma model, not Gemini models, to route a request to a suitable model. (github.com page, read 2026-10-23)
Plan, policy and billing
Gemini CLI's quotas and pricing page says access to the CLI begins with a free tier. (github.com page, read 2026-10-23)
Gemini CLI's quotas and pricing page says a Gemini API key also comes with a free tier. (github.com page, read 2026-10-23)
Gemini CLI's quotas and pricing page says that once the initial requests are used up, a person can keep using the CLI by moving to one of the subscriptions it lists under its paid tier. (github.com page, read 2026-10-23)
Gemini CLI's authentication page says every free tier account, Gemini Code Assist for individuals among them, counts as an individual Google account, as do the paid Google AI Pro and Ultra subscriptions. (github.com page, read 2026-10-23)
Gemini CLI's authentication page says that for most individual Google accounts, free or paid, no Google Cloud project is required for authentication. (github.com page, read 2026-10-23)
Gemini CLI's quotas and pricing page says the pay-as-you-go option is reached by logging in with Vertex AI or with a Gemini API key. (github.com page, read 2026-10-23)
Gemini CLI's quotas and pricing page lists the cost of using a Gemini API key as varying by pricing tier and by model and token usage. (github.com page, read 2026-10-23)
Gemini CLI's quotas and pricing page says that with an API key a person pays per token or per call. (github.com page, read 2026-10-23)
A separate model for planning and for doing
Based on Plan Mode status, Gemini CLI switches between Pro and Flash models, using Pro for planning and Flash for implementation. (github.com page, read 2026-10-19)
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