Open WebUI with 6bee.ai

Open WebUI talks to any OpenAI-compatible API. Add 6bee.ai as a connection and its models appear in the model menu.

Before you start

Open WebUI running, with an admin account.
Create an account with a verified email address, add prepaid balance, then create a key on the console's API keys page. Keep the key secret.

Add the connection

Open Admin Panel → Settings → Connections, and under OpenAI API add a connection:

URL: https://api.6bee.ai/v1
Key: <your key>

Save. The 6bee.ai models are fetched from GET /v1/models and show up in the model menu.

Or set it when you start the container

shell

docker run -d -p 3000:8080 \
  -e OPENAI_API_BASE_URL=https://api.6bee.ai/v1 \
  -e OPENAI_API_KEY=<your key> \
  -v open-webui:/app/backend/data \
  --name open-webui ghcr.io/open-webui/open-webui:main

Background tasks and the concurrency limit

After each answer Open WebUI sends extra requests of its own: a chat title, tags, follow-up suggestions. A 6bee.ai account runs 2 requests at a time, so these can return 429 while an answer is still streaming.

If you see that, open Admin Panel → Settings → Interface and turn off the generation tasks you do not need. Each one is also billed as a normal request.

Input tokens: 1,000,000 uncached tokens per rolling minute. Cache hits don’t count.
Requests: 60 per minute.
Concurrency: 2 requests at a time.

Everyone who uses your Open WebUI shares your key, your balance and these limits. The Terms do not allow reselling access or sharing keys without permission.

Troubleshooting

HTTP 401: The key is missing or wrong. Copy it again from the console, without spaces or quotes.
Model not found: The model ID does not match. List the valid IDs with GET /v1/models or check the console.
HTTP 429: You are over a per-account limit (requests, input tokens or concurrency). The Retry-After header says how long to wait.
HTTP 400 on long sessions: The request no longer fits the model’s context window. Compact or clear the conversation, or switch to a model with a larger window.
Request rejected for balance: Each request first reserves its input plus max_tokens of output. Top up, or lower max_tokens.
No models in the menu: Check that the URL ends in /v1 and that the key was saved. Then reload the page.