Integrations / LiteLLM
Use Badgr as a model provider in LiteLLM
Add Badgr as an OpenAI-compatible upstream in your LiteLLM proxy so every app behind LiteLLM can call it.
The steps follow the tool's documented settings. No tested run is recorded for this page yet.
Why use Badgr for LiteLLM
- Badgr interface
- AI API
- Where LiteLLM fits
- External gateway
- Why Badgr
- Route model requests to Badgr
- Badgr is a drop-in OpenAI-compatible upstream, so adding it is one config entry.
- Your LiteLLM routing, keys and logging stay as they are.
- The same Badgr account also covers GPU jobs and served models if you need more than chat.
What you can do
- Route some traffic from an existing LiteLLM proxy to Badgr
- Give internal teams one LiteLLM URL that also reaches Badgr models
- Fall back to Badgr when another provider is rate limited
Quickstart: LiteLLM config.yaml
model_list:
- model_name: badgr-auto
litellm_params:
model: openai/badgr-auto
api_base: https://aibadgr.com/v1
api_key: os.environ/BADGR_API_KEYHow it works
- 1.Your app calls LiteLLM
- 2.LiteLLM matches the model name to the Badgr entry
- 3.The request goes to Badgr with your key
- 4.The response returns through LiteLLM
What you get
- Chat completions returned through your LiteLLM proxy
Requirements
- A Badgr API key, saved as BADGR_API_KEY (get one at /get-api-key)
- A LiteLLM proxy you can edit (config.yaml)
- LiteLLM version that supports the openai/ provider prefix
What it costs
- AI requests are billed per request at the rate listed for the model you choose (see Models). This page does not quote a fixed price.
- Your application keeps control of how many requests it sends. Use the limits in your own tool to cap usage.
See pricing for how billing works.
Proof
No tested run is recorded for this integration yet. A receipt and example output will be added here after a real run, not before.
Troubleshooting
404 from the upstream
Check that api_base is exactly https://aibadgr.com/v1 with no trailing /chat/completions. LiteLLM adds the path itself.
Model not found
Keep the openai/ prefix on the model value. The part after the slash is the Badgr model name.
401 unauthorized
Confirm BADGR_API_KEY is set in the environment the proxy runs in, not only in your shell.
Developer reference
Ready to start with LiteLLM?
Every run or service has a spending limit you set before it starts.