Use BroadNet Inference in n8n (OpenAI credential, Base URL)
Updated
In n8n, create an OpenAI credential with your BroadNet key as API Key and Base URL set to https://inference.broadnet.ai/v1. In the OpenAI Chat Model node, switch Model from From List to ID, enter a BroadNet ID such as broadnet/glm-5.3, and turn off Use Responses API so n8n calls chat completions.
n8n is a workflow automation tool. Its OpenAI credential has a Base URL field, so the OpenAI Chat Model node (and the other OpenAI nodes that use the credential) can call any OpenAI-compatible API. BroadNet Inference is one. n8n’s docs page for the credential doesn’t show the Base URL field, so the field names below are checked against n8n’s source code as well, linked in the sources.
Setup
Create the credential. In n8n, go to Credentials, create a new OpenAI credential, and fill in:
Field
Value
API Key
your BroadNet key
Organization ID (optional)
leave blank
Base URL
https://inference.broadnet.ai/v1
Save it. n8n tests the credential by calling /models on the Base URL.
Add the model node. Add an AI Agent or Basic LLM Chain node, then attach an OpenAI Chat Model sub-node and select the credential.
Set the model by ID. In Model, switch the mode from From List to ID and enter broadnet/glm-5.3.
Turn off Use Responses API. In n8n’s source, the toggle exists from node version 1.3 and is on by default there. BroadNet serves chat completions, so turn it off.
Set options. Under Options, leave Maximum Number of Tokens at its default (-1) or set it to a few thousand. Max Retries defaults to 2; raise it if you want n8n to retry failed calls more often.
Run the workflow once with a test prompt.
n8n shows a notice when you use a non-OpenAI Base URL: not all models might be chat-compatible or support tools calling or JSON response format. For BroadNet, chat works on every chat model, but BroadNet’s docs list tools and structured output only for GLM 5.3 and Qwen3.8 27B.
Which model to pick
Workflow
Model
Why
AI Agent with tools
broadnet/glm-5.3
Tools and structured output listed by BroadNet
Images, Arabic messages
broadnet/qwen3.8-27b
Tools, image input, tested in Arabic
High-volume classification
broadnet/gemma-4-26b-a4b
Low per-token price; no reasoning listed
Long documents
broadnet/deepseek-v4.1-flash
1M context; tools not listed
Compare prices on the pricing page. For audio, n8n’s HTTP Request node can post files to /v1/audio/transcriptions; the Arabic speech-to-text guide shows the form fields to send.
Troubleshooting
Credential test fails. Check the Base URL ends in /v1 with no trailing path. If chat calls also return 401, the key is wrong, expired, or out of pay-as-you-go allowance.
Model errors. Use the ID mode and enter the exact BroadNet ID with the broadnet/ prefix. GLM 5.3, Qwen3.8 27B and DeepSeek V4.1 Flash need a top-up; the $5 starting credit covers BroadNet Gemma 4 VL 26B.
“Bad request - please check your parameters”. n8n’s docs suggest repeating the call in an HTTP Request node to see the full error. A common cause here is the Responses API toggle.
429 in loops. A pay-as-you-go key allows 30 requests a minute and 4 at once. n8n’s docs suggest Loop Over Items with a Wait node to pace batches. See errors and retries.
Parallel executions on a plan key. An unlimited plan session runs one request at a time. Parallel workflow executions queue unless each has its own session.
Prefer code? The same settings work in LangChain, which n8n’s AI nodes are built on.
Questions
Why does the n8n AI Agent fail with BroadNet?
Check that Use Responses API is off in the OpenAI Chat Model node. In node version 1.3 it is on by default, and BroadNet serves /v1/chat/completions, not the Responses API. Also set Model to ID mode with the exact BroadNet ID.
Why is the model dropdown empty or wrong?
The From List mode reads the provider's /models endpoint. BroadNet's docs describe that endpoint as public catalog metadata for monitors. Switch Model to ID mode and type the BroadNet model ID.
Why does the n8n agent return an empty output?
The reasoning used up Maximum Number of Tokens. Raise it, or leave it at the default of -1.
Where is the Base URL field in n8n's OpenAI credential?
It is in the OpenAI credential itself, below API Key and Organization ID. Its default is https://api.openai.com/v1. Replace it with https://inference.broadnet.ai/v1, keeping /v1 and adding no further path.