Integrations / One API
ConnectDocumented
Connect One API to Badgr
Add Badgr as an OpenAI-type channel in One API so your gateway users can call Badgr models.
The steps follow the tool's documented settings. No tested run is recorded for this page yet.
Why use Badgr for One API
- Badgr interface
- AI API
- Where One API fits
- External gateway
- Why Badgr
- Model upstream
- Add Badgr as one more OpenAI-type channel without changing how your users call One API.
- Per-token billing at listed rates, which you can limit with One API quotas.
- A single upstream for chat, plus jobs and services on the same account.
What you can do
- Share one Badgr key across many gateway users
- Meter and limit usage per gateway token
- Expose Badgr under your own model names
Quickstart: One API channel settings
- In One API, open Channels and add a channel of type OpenAI.
- Set the proxy base URL to https://aibadgr.com (One API adds /v1 itself).
- Paste your Badgr API key as the channel key.
- Add the model badgr-auto to the channel's model list.
- Test the channel, then call it through your One API token.
How it works
- 1.A gateway user calls One API with a One API token
- 2.One API picks the Badgr channel for that model
- 3.The request goes to Badgr with your key
- 4.Usage is counted in One API and billed by Badgr
What you get
- Chat completions served through your gateway
Requirements
- A Badgr API key, saved as BADGR_API_KEY (get one at /get-api-key)
- Admin access to a One API instance
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.
- One API quotas are separate from Badgr billing. Set them so they stay under what you want to spend.
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
Channel test fails with 404
Remove any /v1 suffix from the base URL. If it still fails, try the full https://aibadgr.com/v1 form, since One API versions differ.
Model not listed for users
Add the model name to the channel and to the token's allowed models.
Wrong model name sent
Use the model mapping field to translate your public name to badgr-auto.
Developer reference
Ready to start with One API?
Every run or service has a spending limit you set before it starts.