Does Gemini CLI need a plugin or a fork?

No. The router speaks the Gemini API at /v1beta, so the CLI keeps its own dialect and key variable. The router is a standard endpoint; the tool is unchanged.

Which model does the tool get?

Whatever it asks for. The name auto lets the router choose per turn under your policy; a model id pins it and still routes among its providers; a workspace alias maps the tool's own default name to either.

What does the router add that the tool does not have?

One key and one bill for Gemini, OpenAI and Anthropic models. The team's policy in front of every turn. A trace per call.

Can I use my own provider keys?

Yes - connect them under Model providers and the router executes on your accounts; model usage is billed by the provider, the platform meters requests.

Gemini CLI through the router

Gemini CLI through the router: the same governance every other tool gets.

Launch Gemini CLI with the router as its Gemini API endpoint - generateContent, streaming and countTokens are served natively. The workspace policy, budgets, redaction and the trace apply to every turn, and auto lets the router choose the model when Gemini is not the best value for the task.

One key and one bill for Gemini, OpenAI and Anthropic models
The team's policy in front of every turn
A trace per call

Create a free account Gemini CLI docs

One commandbash

pip install opensmartroute
osr login                      # once: a browser sign-in, or --token osr_live_...
osr run gemini-cli          # Gemini CLI starts with the router as its endpoint

Or by hand - geminibash

export GOOGLE_GEMINI_BASE_URL=https://api.opensmartroute.ai
export GEMINI_API_KEY=$OSR_API_KEY
export GEMINI_MODEL=auto
gemini

Gemini CLI speaks the Google Gemini API; the router serves generateContent, streamGenerateContent and countTokens at /v1beta with function calling, images and streaming translated both ways.

Verify

The first turn is on the activity page.

Send one message from the tool and read the row: the model that answered, the cost, the confidence and a link to the full trace with the alternatives and the policy decisions.

verify.shbash

# the tool's next turn is on the activity page with its cost, model and trace
curl -s https://api.opensmartroute.ai/api/v1/activity?limit=3 -H "Authorization: Bearer $OSR_API_KEY"

Questions

Gemini CLI and the router

Does Gemini CLI need a plugin or a fork?: No. The router speaks the Gemini API at /v1beta, so the CLI keeps its own dialect and key variable. The router is a standard endpoint; the tool is unchanged.
Which model does the tool get?: Whatever it asks for. The name auto lets the router choose per turn under your policy; a model id pins it and still routes among its providers; a workspace alias maps the tool's own default name to either.
What does the router add that the tool does not have?: One key and one bill for Gemini, OpenAI and Anthropic models. The team's policy in front of every turn. A trace per call.
Can I use my own provider keys?: Yes - connect them under Model providers and the router executes on your accounts; model usage is billed by the provider, the platform meters requests.

Other tools

The same router behind every tool the team runs.

Put Gemini CLI behind the router today.

A free account, one key, one command. Every turn the tool makes is priced, governed and explained from then on.

Create a free account Migrating application code instead?

Free plan, no card. Fifteen thousand decisions a month with the full trace.