Use n8n with Chinese AI models through ChinaAPI.

Setup

Create OpenAI credentials with a custom base URL.

1. In n8n, open Credentials and create new OpenAI credentials, or create them from an OpenAI/Chat OpenAI/LM OpenAI node.
2. Choose API key authentication.
3. Paste your ChinaAPI token into API Key. Leave Organization ID blank unless your n8n build requires a value.
4. Set the custom base URL, base URL, or API endpoint field to https://dash.chinaapi.ai/v1. Some n8n versions show this under additional options.
5. Save the credential.
6. In an AI Agent, Chat Model, LM OpenAI, or OpenAI node, select the credential and enter an exact model ID such as deepseek-v4-flash.

Copy-paste test

Use a simple AI node prompt.

Return JSON only:
{"status":"connected","provider":"ChinaAPI","tool":"n8n"}

If the node supports manual model entry, use deepseek-v4-flash for the first run and keep temperature low.

Troubleshooting

Common n8n issues.

Thinking models such as qwen3.7-max can generate reasoning tokens before returning final output. Enable streaming if the node supports it or raise the n8n node/execution timeout for long tasks.

Model not found: check the exact model ID on live pricing. If the n8n node has a model dropdown only, look for a manual/custom model option.

401: confirm your OpenAI credential uses the sk-... ChinaAPI key and the request is sent with a bearer authorization header. Re-save the credential after changing the base URL.