# Use Xantly with Gemini CLI

[Gemini CLI](https://github.com/google-gemini/gemini-cli) is Google's official command-line tool for Gemini, built for agent workflows with tool calling, MCP support, and grounding. As shipped, it's locked to Google's `generativelanguage.googleapis.com` endpoint. Xantly **does** route to Gemini models natively (via Google's API), but Gemini CLI doesn't yet accept a custom base URL. This page covers both the current best-fit patterns and the future Xantly-direct option if/when that flag lands.

## Current state (April 2026)

| What works | What doesn't |
|---|---|
| Use Gemini CLI with a direct Google API key | Set a custom base URL |
| Access Gemini models through Xantly via [OpenCode](/docs/use-with-opencode) / any other tool | Point Gemini CLI itself at Xantly |
| BYOK your Google API key into Xantly and route other tools through it | Native Xantly gateway in Gemini CLI |

Track the upstream issue: [github.com/google-gemini/gemini-cli, base URL override](https://github.com/google-gemini/gemini-cli/issues/custom-endpoint).

## Option 1, Use OpenCode with Gemini (recommended)

If you want a Gemini-heavy CLI workflow with Xantly's benefits, [OpenCode](/docs/use-with-opencode) natively routes to Gemini via Xantly:

```jsonc
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "xantly": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://api.xantly.com/v1",
        "apiKey": "xantly_sk_..."
      },
      "models": {
        "google/gemini-2.5-pro":   { "name": "Gemini 2.5 Pro (via Xantly)" },
        "google/gemini-2.5-flash": { "name": "Gemini 2.5 Flash (via Xantly)" }
      }
    }
  },
  "model": "google/gemini-2.5-pro"
}
```

You get Gemini + smart routing + cache + waterfall fallback. See the [OpenCode integration](/docs/use-with-opencode) for full details.

## Option 2, Use Gemini CLI directly, BYOK your Google key to Xantly for other tools

If you like Gemini CLI specifically and want to keep using it:

1. Use Gemini CLI with your direct Google API key (unchanged).
2. For all other tools (Cline, Continue.dev, Aider, OpenCode), point them at Xantly.
3. Register your Google API key as a [BYOK](/docs/bring-your-own-key) key in your Xantly dashboard, Xantly will use it for Gemini routing in other tools, so you don't double-pay.

```bash
# Gemini CLI, direct to Google
export GEMINI_API_KEY=ya29...   # direct Google key

# Everything else, through Xantly
export OPENAI_API_BASE=https://api.xantly.com/v1
export OPENAI_API_KEY=xantly_sk_...
```

## Option 3, When Gemini CLI adds custom-endpoint support

If/when Gemini CLI ships a `--base-url` flag or a `GEMINI_BASE_URL` env var, the setup will be:

```bash
export GEMINI_BASE_URL=https://api.xantly.com        # bare, Xantly's /v1beta/models/... is Gemini-shape compatible
export GEMINI_API_KEY=xantly_sk_...
```

Xantly's Gemini-native endpoint at `https://api.xantly.com/v1beta/models/...` already speaks the Gemini wire protocol (see [Provider Ecosystem](/docs/platform-overview)). Gemini CLI would just need to honor a custom base.

## Current workaround for CLI-only users

Aider + Gemini is the closest single-CLI equivalent:

```bash
aider \
  --openai-api-base https://api.xantly.com/v1 \
  --openai-api-key xantly_sk_... \
  --model google/gemini-2.5-pro
```

See [Aider integration](/docs/use-with-aider) for details.

## Model choice (via Xantly)

| Model ID | When |
|---|---|
| `google/gemini-2.5-pro` | Primary Gemini workflow, large context. |
| `google/gemini-2.5-flash` | Fast + cheap Gemini. |
| `xantly/auto-quality` | If you'd rather let BaRP pick, often picks Claude/GPT over Gemini for coding. |

## Verify (via OpenCode)

```bash
cd some-project
opencode  # with the Gemini config above
> list files here
```

Check the Xantly dashboard, call logs as `google/gemini-2.5-pro` with routing metadata.

## What you get

- **Gemini + smart routing.** Xantly's waterfall transparently falls back to GPT/Claude if Gemini 5xx's.
- **Semantic cache** on Gemini queries.
- **Cost visibility** per call.
- **BYOK routing.** Use your Google AI Studio credits through Xantly.
- **Memory** across sessions.

## Gotchas

**Gemini CLI ≠ Gemini API ≠ Vertex AI.** Three different Google surfaces. Xantly currently routes to the public Gemini API (`generativelanguage.googleapis.com`). Vertex AI support is on the roadmap.

**Gemini 2.5 Pro context is 2M tokens**: absurdly long. Xantly's waterfall treats Gemini 2.5 Pro as the long-context fallback when other models hit their window. Your Gemini CLI experience benefits from this when routed via Xantly-aware tools.

**Gemini function-calling JSON shape.** Gemini's tool format differs from OpenAI's. Xantly's normalizer translates it both ways, for your tool-heavy workflows, this means you can switch `model=google/...` to `model=openai/...` without rewriting tool schemas.

## Next steps

- [OpenCode](/docs/use-with-opencode), the best CLI surface for Gemini + Xantly today.
- [Aider](/docs/use-with-aider), terminal pair programmer, works with Gemini via Xantly.
- [Bring Your Own Key](/docs/bring-your-own-key), connect your Google AI Studio key to Xantly.
- [Migrate from Antigravity](/docs/migrate-from-antigravity), if you came from Google's AI coding product.