LiteLLM is an open-source LLM gateway with a unified API to 100+ model providers. Route Apus through LiteLLM for centralized cost tracking, logging, virtual keys with spend limits, and backend failover without changing Apus config.

Quick start

```bash
apus onboard --auth-choice litellm-api-key
```

For non-interactive setup against a remote proxy, pass the proxy URL explicitly:

```bash
apus onboard --non-interactive --accept-risk --skip-health --auth-choice litellm-api-key \
  --litellm-api-key "$LITELLM_API_KEY" --custom-base-url "https://litellm.example/v1"
```

    LiteLLM calls the upstream provider on your behalf, so export that
    provider's key before starting it — `ANTHROPIC_API_KEY` for the model
    below. See [Model routing](#advanced) for multi-backend setups.

    ```bash
    pip install 'litellm[proxy]'
    export ANTHROPIC_API_KEY=sk-ant-...
    litellm --model claude-opus-4-6
    ```

    ```bash
    export LITELLM_API_KEY="your-litellm-key"
    apus
    ```

Configuration

{
  models: {
    providers: {
      litellm: {
        baseUrl: "http://localhost:4000",
        apiKey: "${LITELLM_API_KEY}",
        api: "openai-completions",
        models: [
          {
            id: "claude-opus-4-6",
            name: "Claude Opus 4.6",
            reasoning: true,
            input: ["text", "image"],
            contextWindow: 200000,
            maxTokens: 64000,
          },
          {
            id: "gpt-6-astra",
            name: "GPT-6 Astra",
            reasoning: true,
            input: ["text", "image"],
            contextWindow: 1050000,
            maxTokens: 128000,
          },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "litellm/claude-opus-4-6" },
    },
  },
}

The default model onboarding writes is litellm/claude-opus-4-6.

In merge mode, onboarding with an explicit proxy URL preserves any authored provider models and otherwise leaves the provider model list empty for discovery. Run apus models list --provider litellm --refresh --json to list the proxy's models. With models.mode: "replace", discovery is disabled, so onboarding keeps the documented default in the provider model list while preserving existing model definitions.

Image generation

LiteLLM can back the image_generate tool through OpenAI-compatible /images/generations and /images/edits routes. Default image model is gpt-image-2; configure a different one under agents.defaults.mediaModels.image:

{
  models: {
    providers: {
      litellm: {
        baseUrl: "http://localhost:4000",
        apiKey: "${LITELLM_API_KEY}",
      },
    },
  },
  agents: {
    defaults: {
      mediaModels: {
        image: {
          primary: "litellm/gpt-image-2",
          timeoutMs: 180000,
        },
      },
    },
  },
}

Loopback LiteLLM URLs (http://localhost:4000, 127.0.0.1, ::1, host.docker.internal) work without a global private-network override. For a LAN-hosted proxy, set models.providers.litellm.request.allowPrivateNetwork: true because the API key is sent to that host.

Advanced

Create a dedicated key for Apus with spend limits:

```bash
curl -X POST "http://localhost:4000/key/generate" \
  -H "Authorization: Bearer $LITELLM_MASTER_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "key_alias": "apus",
    "max_budget": 50.00,
    "budget_duration": "monthly"
  }'
```

Use the generated key as `LITELLM_API_KEY`.

LiteLLM can route model requests to different backends. Configure in your LiteLLM `config.yaml`:

```yaml
model_list:
  - model_name: claude-opus-4-6
    litellm_params:
      model: claude-opus-4-6
      api_key: os.environ/ANTHROPIC_API_KEY

  - model_name: gpt-6-astra
    litellm_params:
      model: gpt-6-astra
      api_key: os.environ/OPENAI_API_KEY
```

Apus keeps requesting `claude-opus-4-6`; LiteLLM handles the routing.

```bash
# Key info
curl "http://localhost:4000/key/info" \
  -H "Authorization: Bearer sk-litellm-key"

# Spend logs
curl "http://localhost:4000/spend/logs" \
  -H "Authorization: Bearer $LITELLM_MASTER_KEY"
```

- LiteLLM runs on `http://localhost:4000` by default.
- Apus connects through LiteLLM's proxy-style OpenAI-compatible `/v1` endpoint.
- Native-OpenAI-only request shaping does not apply through a configured LiteLLM base URL:
  no `service_tier`, no Responses `store`, no prompt-cache hints, no OpenAI reasoning-effort
  payload shaping.
- Hidden Apus attribution headers (`originator`, `version`, `User-Agent`) are only sent to
  verified native OpenAI endpoints, so they are not injected on a custom LiteLLM base URL.

Related

Official LiteLLM documentation and API reference.

Overview of all providers, model refs, and failover behavior.

Full config reference.

How to choose and configure models.