Open WebUI with FluxCDN AI
Open WebUI runs on your own server or computer and opens in a browser. A connection the admin creates goes from the Open WebUI server to FluxCDN and fetches the model list by itself.
- Licence:
- Open WebUI License: BSD-3 based with a branding clause; not OSI open source
- Platforms:
- Self-hosted (Docker, pip); any browser
- Address (OpenAI-compatible):
https://ai.fluxcdn.cloud/api/v1
Before you start
- Create an API key. On the API keys page press “Create key” and copy the key right away. It starts with
flux_live_and is never shown in full again. - Give agents a key of their own and set a daily or monthly spending limit on it with “Limits”. Agents send request after request by themselves; the limit stops spending you didn't expect.
- Have some credit in the account (Billing).
- In the examples, put your own key where it says
flux_live_YOUR_KEY.
Set it up
Step 1: Add a connection
As an admin: Settings → Admin → Connections, under Manage OpenAI API Connections press + Add Connection. Enter the address and key, press Verify Connection, then Save. Leave Model IDs empty to get every model, or list just a few ids.
Admin → ConnectionsURL: https://ai.fluxcdn.cloud/api/v1 API Key: flux_live_YOUR_KEYWith Docker, the variables are read only on the first start and then kept in the database; make later changes in the settings.
Step 2: A cheap model for small tasks
Open WebUI also calls a model for titles, tags and follow-up suggestions. In the admin settings, set the external Task Model to a cheap model such as
deepseek/deepseek-v4-flash(in Docker:TASK_MODEL_EXTERNAL).
Check it works
Step 1: The connection, then a chat
Verify Connection fetches the model list from FluxCDN. Then pick a model such as
anthropic/claude-sonnet-5.5in a new chat and send a message.
Troubleshooting
- The model list is very long
- List only the ids you want under the connection's Model IDs. That list replaces the full one.
- Users' Direct Connections give a network error
- That connection goes from the user's browser, and FluxCDN now answers it. Check the address and the key.
- Error 401 or
invalid_api_key - The key wasn't copied whole, was revoked, or went in the wrong field. It starts with
flux_live_and has no spaces. If the tool reads it from an environment variable, open a new terminal or window after setting it. - Error 402,
insufficient_credit(in Codex:insufficient_quota) although you have credit - Before each request, the most it could cost is set aside from your credit. When the answer ends, only the real cost is taken and the rest is released. A tool that asks for a very long output on every request sets aside a large amount. Lower the tool's output limit (for example to 32000 tokens) or add credit.
- Error 404 or
model_not_found - The model id must be exactly as on the models page, with the maker's prefix:
anthropic/claude-sonnet-5.5, notclaude-sonnet-5.5. Lower case and dots matter. Copy the id rather than typing it. - A 404 that doesn't mention the model
- The base address is wrong. Most tools want
https://ai.fluxcdn.cloud/api/v1and add the rest themselves; don't write/chat/completionstwice and don't leave out/v1. See the which address table. - Error 429:
rate_limit_exceededorbudget_exceeded - Either requests per minute went over the limit (wait a little; most tools retry by themselves), or this key's spending today or this month reached its limit. See it on API keys under “Limits”.
- Error 502, 503, 504 or 529
- The model's service was briefly unavailable. Send again; most tools do it themselves. A request that fails before answering costs nothing. If it lasts, switch to another model for a while.
Limits
- Documents (RAG) work with Open WebUI's own local embedder. Don't point
RAG_EMBEDDING_ENGINEat FluxCDN; we have no embeddings. - Open WebUI's own image generation and speech features need
/imagesand/audioand don't work through FluxCDN. Use its local or browser engines for those.

