N8n OPEN AI time request help!

Questions
1

Hi everyone,
I’m running n8n v2.9.4 inside Easypanel on a Hostinger VPS (KVM2). Everything works fine except for one issue: whenever I use OpenAI (ChatGPT node or HTTP request to the OpenAI API), the execution fails after around 10 seconds with a timeout error. Give me this: {
“errorMessage”: “Request timed out.”,
“errorDetails”: {},
“n8nDetails”: {
“time”: “5/3/2026, 19:52:16”,
“n8nVersion”: “2.9.4 (Self Hosted)”,
“binaryDataMode”: “filesystem”
}
}

1 Like
2

Welcome to the n8n community @Alejandro_Medranda1

The OpenAI timeout error you’re experiencing after 10 seconds is likely caused by network/firewall restrictions on your Hostinger VPS or timeout configuration in n8n/Easypanel.

Possible workaround include:

1. Increase n8n Timeout Settings

Add these environment variables to your n8n configuration in Easypanel:

environment:
  - EXECUTIONS_TIMEOUT=300  # 5 minutes
  - EXECUTIONS_TIMEOUT_MAX=600  # 10 minutes max
  - N8N_DEFAULT_TIMEOUT=120000  # 2 minutes in milliseconds

In Easypanel:

  • Go to your n8n app settings

  • Find “Environment Variables”

  • Add the variables above

  • Restart the app

2. Increase HTTP Request Timeout (if using HTTP Request node)

In your HTTP Request node configuration:

  • Scroll to “Options”

  • Set Timeout: 120000 (2 minutes in milliseconds)

  • This overrides the default 10-second timeout

3. Check Hostinger Firewall

Hostinger VPS may have firewall rules blocking OpenAI:

# SSH into your VPS
ssh root@your-vps-ip

# Check if you can reach OpenAI
curl -I https://api.openai.com/v1/models

# Test with timeout
curl --max-time 30 https://api.openai.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-3.5-turbo","messages":[{"role":"user","content":"test"}]}'

If this times out, you have a network/firewall issue.

4. Configure Easypanel Proxy Timeout

Easypanel uses Traefik as a reverse proxy. It may have its own timeout:

In your Easypanel app settings, add these labels (if available):

labels:
  - "traefik.http.services.n8n.loadbalancer.responseforwarding.flushinterval=100ms"
  - "traefik.http.middlewares.n8n-timeout.timeout.read=300s"
  - "traefik.http.middlewares.n8n-timeout.timeout.write=300s"

5. Use Streaming (if available)

For ChatGPT node, enable streaming to avoid timeouts:

  • In the ChatGPT node options

  • Look for “Stream” or “Streaming” option

  • Enable it (this sends partial responses, preventing timeouts)

6. Test with Shorter Prompts

To isolate the issue:

  • Try a very short prompt: “Say hello”

  • If this works, the issue is response time, not connectivity

  • If this also times out, it’s a network/firewall issue

7. Check DNS Resolution

Sometimes DNS issues cause delays:

# SSH into VPS
nslookup api.openai.com

# If slow or failing, add Google DNS
echo "nameserver 8.8.8.8" | sudo tee /etc/resolv.conf
echo "nameserver 8.8.4.4" | sudo tee -a /etc/resolv.conf

8. Verify OpenAI API Key

Invalid API keys can cause timeouts:

Complete n8n Configuration for Easypanel:

In Easypanel, set these environment variables:

N8N_HOST=your-domain.com
N8N_PROTOCOL=https
WEBHOOK_URL=https://your-domain.com/
EXECUTIONS_TIMEOUT=300
EXECUTIONS_TIMEOUT_MAX=600
N8N_DEFAULT_TIMEOUT=120000
NODE_OPTIONS=--max-old-space-size=2048

Try these in order and let me know which one resolves it!

3

Hi @Alejandro_Medranda1 Welcome!
Consider updating to the latest version , also increasing the AI agent node’s timeout would also be a better take! And revoke your current set of tokens and use a fresh token and then try again.

4

Hey welcome! 10 seconds is way too fast to be an n8n timeout, that’s almost certainly Easypanel’s Traefik proxy cutting the connection. You need to add a custom Traefik config at /etc/easypanel/traefik/config/custom.yaml and bump the respondingTimeouts.readTimeout up. Also worth checking if your Docker MTU matches your VPS network MTU since Hostinger seems to have issues with that specifically.

5

@Alejandro_Medranda1 building on what @achamm said — the Traefik proxy in Easypanel is almost certainly the culprit. The 10-second cutoff is Traefik’s default respondingTimeout, not n8n’s internal timeout.

Here is the specific fix. Create or edit /etc/easypanel/traefik/config/custom.yaml on your VPS:

entryPoints:
  websecure:
    transport:
      respondingTimeouts:
        readTimeout: 300s
        writeTimeout: 300s
        idleTimeout: 300s
  web:
    transport:
      respondingTimeouts:
        readTimeout: 300s
        writeTimeout: 300s
        idleTimeout: 300s

Then restart the Traefik container:

docker restart easypanel_traefik_1

(container name may differ — check with docker ps | grep traefik)

Also worth doing while you are in there: add N8N_DEFAULT_BINARY_DATA_TTL=60 and increase your node-level timeout in the OpenAI node settings from the default 60s to 180s+.

If the issue persists after fixing Traefik, the second most common cause on Hostinger VPS is a firewall rule blocking persistent HTTPS connections after a few seconds. You can test with: curl -v --max-time 30 https://api.openai.com/v1/models from inside the VPS — if it hangs and drops around 10 seconds, it is a network-level issue rather than Traefik.

6

Guys, doesnt work, help me please my discord please help me: Skayly