n8n with FluxCDN AI
n8n (cloud or on your own server) has an address field in its OpenAI credential. That is all it takes for the AI Agent, Basic LLM Chain and OpenAI nodes to run on FluxCDN models.
- Licence:
- Sustainable Use License (fair-code; not OSI open source)
- Platforms:
- Self-hosted (Docker, npm) or n8n Cloud
- Address (OpenAI-compatible):
https://ai.fluxcdn.cloud/api/v1- Address (Full request address):
https://ai.fluxcdn.cloud/api/v1/chat/completions
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: Create an OpenAI credential
Credentials → Create credential → OpenAI. Enter the key, leave Organization ID empty and change Base URL. On Save n8n tests the connection. Put the address in the credential itself, not in a node's Base URL option.
Credentials → OpenAIAPI Key: flux_live_YOUR_KEY Base URL: https://ai.fluxcdn.cloud/api/v1Step 2: Set up the model node
Give the AI Agent (or Basic LLM Chain) node an OpenAI Chat Model and choose the credential. Switch Model from From list to By ID and type the id, for example
anthropic/claude-sonnet-5.5. Turn off Use Responses API: FluxCDN has that route too, but OpenAI's built-in tools (Web Search, File Search, Code Interpreter) don't work this way and Chat Completions is simpler.Step 3: For anything else: the HTTP Request node
When a node doesn't take an address, send the request with HTTP Request and read the answer from
choices[0].message.content.HTTP RequestMethod: POST URL: https://ai.fluxcdn.cloud/api/v1/chat/completions Headers: Authorization: Bearer flux_live_YOUR_KEY Body (JSON): { "model": "deepseek/deepseek-v4-flash", "messages": [{ "role": "user", "content": "{{ $json.text }}" }] }
Check it works
Step 1: The credential, then a message
Saving the credential should show “Connection tested successfully”. Then, in a workflow with a Chat Trigger, press Open chat and send “hello”.
Troubleshooting
- The AI Agent calls no tools or fails
- The AI Agent needs at least one tool and a model that supports tools. Pick a model with the Tools label, and turn on JSON responses only when the model supports them.
- 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. - An error about
previous_response_idor OpenAI's built-in tools (web search, file search, code interpreter) - Some tools switch to the Responses API without saying so. FluxCDN has it, but without memory (the whole conversation is sent each time) and without the tools that run on OpenAI's servers. Set the tool to Chat Completions: in n8n turn off Use Responses API, in Continue
useResponsesApi: false, in the Vercel AI SDKopenai.chat(...), in LangChainuse_responses_api=False. - 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
- Vector store and RAG nodes need an embedding model; take it from another provider.
- The OpenAI node's Image, Audio and File operations call
/images,/audioand/files, which FluxCDN doesn't have.

