Dify with FluxCDN AI
Dify (cloud or on your own server) connects to FluxCDN with the official “OpenAI-API-compatible” plugin. You add each model separately. Only the workspace's owners and admins can add providers.
- Licence:
- Dify Open Source License (Apache-2.0 based, with extra conditions)
- Platforms:
- Self-hosted (Docker) or Dify Cloud
- 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: Install the plugin
Integrations → Model Provider and install the OpenAI-API-compatible plugin (or from marketplace.dify.ai).
Step 2: Add a model
On the plugin's card press Add Model and enter these values. For agents Function Call Type must be Tool Call; its default is “Not Support”. Turn on Vision Support only for models that understand images. Take the sizes from the model's own page. Repeat for each other model.
OpenAI-API-compatible → Add ModelModel Type: LLM Model Name: anthropic/claude-sonnet-5.5 API Key: flux_live_YOUR_KEY API Base URL: https://ai.fluxcdn.cloud/api/v1 Completion mode: Chat Model context size: 1000000 Upper bound for max tokens: 32000 Function Call Type: Tool Call Stream function calling: Support Vision Support: Support API Type: Chat Completions API (/chat/completions)
Check it works
Step 1: Save, then preview
On Save the plugin sends a tiny request (“ping”); its cost is negligible. Then use the model in a Chatflow and preview it.
Troubleshooting
- The agent falls back to ReAct instead of tools
- Set the model's Function Call Type to Tool Call.
- 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invalid_api_key - The key wasn't copied whole, was revoked, or went in the wrong field.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
- Dify's knowledge bases need an embedding model; add it from another provider.

