Skip to content
FluxCDNFluxCDN
esc
On this page

DocsTools guide

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
The tool's own docs ↗

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

  1. 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 → OpenAI
    API Key:   flux_live_YOUR_KEY
    Base URL:  https://ai.fluxcdn.cloud/api/v1
  2. Step 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.

  3. 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 Request
    Method:   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

  1. 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, not claude-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/v1 and add the rest themselves; don't write /chat/completions twice and don't leave out /v1. See the which address table.
An error about previous_response_id or 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 SDK openai.chat(...), in LangChain use_responses_api=False.
Error 429: rate_limit_exceeded or budget_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, /audio and /files, which FluxCDN doesn't have.

What doesn't work this way →