LiteLLM

LiteLLM

LiteLLM is an open-source LLM gateway that provides a unified API to 100+ model providers. Route Agdi through LiteLLM to get centralized cost tracking, logging, and the flexibility to switch backends without changing your Agdi config.

Why use LiteLLM with Agdi?

• Cost tracking — See exactly what Agdi spends across all models
• Model routing — Switch between Claude, GPT-4, Gemini, Bedrock without config changes
• Virtual keys — Create keys with spend limits for Agdi
• Logging — Full request/response logs for debugging
• Fallbacks — Automatic failover if your primary provider is down

Quick start

Via onboarding

agdi onboard --auth-choice litellm-api-key

Manual setup

1. Start LiteLLM Proxy:

pip install 'litellm[proxy]'
litellm --model claude-opus-4-6

2. Point Agdi to LiteLLM:

export LITELLM_API_KEY="your-litellm-key"

agdi

That’s it. Agdi now routes through LiteLLM.

Configuration

Environment variables

export LITELLM_API_KEY="sk-litellm-key"

Config file

{
  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-4o",
            name: "GPT-4o",
            reasoning: false,
            input: ["text", "image"],
            contextWindow: 128000,
            maxTokens: 8192,
          },
        ],
      },
    },
  },
  agents: {
    defaults: {
      model: { primary: "litellm/claude-opus-4-6" },
    },
  },
}

Virtual keys

Create a dedicated key for Agdi with spend limits:

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

Use the generated key as LITELLM_API_KEY.

Model routing

LiteLLM can route model requests to different backends. Configure in your LiteLLM config.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-4o
    litellm_params:
      model: gpt-4o
      api_key: os.environ/OPENAI_API_KEY

Agdi keeps requesting claude-opus-4-6 — LiteLLM handles the routing.

Viewing usage

Check LiteLLM’s dashboard or API:

# 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"

Notes

• LiteLLM runs on http://localhost:4000 by default
• Agdi connects via the OpenAI-compatible /v1/chat/completions endpoint
• All Agdi features work through LiteLLM — no limitations

See also

• LiteLLM Docs
• Model Providers