You are missing trading opportunities:
- Free trading apps
- Over 8,000 signals for copying
- Economic news for exploring financial markets
Registration
Log in
You agree to website policy and terms of use
If you do not have an account, please register
i have it also the same problem
Forum on trading, automated trading systems, and trading strategy testing
New MetaTrader 5 Platform Build 6180: More AI Features
Renat Fatkhullin , 2026.09.15 17:38
There was a problem with the LLM router overload due to the load in the last 3 days.
Please try it now.
Thank you. It's already working for me as I mentioned in Post #19.
I probably should have been more detailed as to the specific issues. Sessions were stalling, going in circles on repeat, and stacking up by spontaneously resurrecting themselves. Renat's diagnosis certainly explains that.
Just as additional information, I had a very similar situation, which is how I found this thread.
Even a simple “hello” took a long time to get a response because of checks such as get_workspace_info . For slightly more complex requests, the session would repeatedly retry and eventually time out.
I deleted the " llm-agent " folder and restarted MT5. All previous session history was lost, but the AI Assistant started responding quickly again.
I then restored the backed-up files, and it has continued to work normally.
Perhaps something was reset by deleting the folder, although I have no way to confirm the cause. This is only what I observed in my own environment, but I thought it might be useful as a reference.
Just as additional information, I had a very similar situation, which is how I found this thread.
Even a simple “hello” took a long time to get a response because of checks such as get_workspace_info . For slightly more complex requests, the session would repeatedly retry and eventually time out.
I deleted the " llm-agent " folder and restarted MT5. All previous session history was lost, but the AI Assistant started responding quickly again.
I then restored the backed-up files, and it has continued to work normally.
Perhaps something was reset by deleting the folder, although I have no way to confirm the cause. This is only what I observed in my own environment, but I thought it might be useful as a reference.
For the record, deleting the folder was ineffective on my end. The only thing that fixed it was Alain's report to the Admin's and the Admin's subsequent fix. Such a problem residing on the LLM router can't be fixed from the client-side.
Forum on trading, automated trading systems, and trading strategy testing
New MetaTrader 5 Platform Build 6180: More AI Features
Renat Fatkhullin , 2026.09.15 17:38
There was a problem with the LLM router overload due to the load in the last 3 days.
Please try it now.
Hello,
I am experiencing the same MT5 AI Assistant connection problem reported by other users.
My tests show:
DNS: api1.inferdeck.net → 194.164.179.53
Ping: 0% packet loss
TCP 443: successful
HTTPS: SSL/TLS trust failure
Certificate: CN=*.inferdeck.net
Let's Encrypt certificate expired on September 26, 2026 at 13:55:26
Please check the InferDeck endpoint/certificate and MT5 AI Assistant infrastructure.
Thank you.
Hello,
I am experiencing the same MT5 AI Assistant connection problem reported by other users.
My tests show:
DNS: api1.inferdeck.net → 194.164.179.53
Ping: 0% packet loss
TCP 443: successful
HTTPS: SSL/TLS trust failure
Certificate: CN=*.inferdeck.net
Let's Encrypt certificate expired on September 26, 2026 at 13:55:26
Please check the InferDeck endpoint/certificate and MT5 AI Assistant infrastructure.
Thank you.
Forum on trading, automated trading systems and testing trading strategies
New MetaTrader 5 Platform Build 6230: Expanded AI Capabilities
Ryan L Johnson, 2026.09.26 12:19
Is there a server overload again today?
MT5 Beta Build 6230, MQL5 Lite, MCP enabled, api2.inferdeck.net.
Prompt
Confirm your access to api2.inferdeck.net.
Response
Network error: Could not connect to api2.inferdeck.net — check your network connection and try again.
Please resend your message to try again.
[Prompt and Response repeated. No settings changed from yesterday when connection succeeded.]
Post edit:
api2.inferdeck.net is down again:
api1.inferdeck.net is down again:
api2.inferdeck.net is down again:
api1.inferdeck.net is down again:
It's unavailable for me too.
It's unavailable for me too.
I encountered the same issue this morning. When I entered https://api1.inferdeck.net, the endpoint was automatically switched to https://api4.inferdeck.net, and the connection was established successfully.
This matches the suggestion from Ryan L Johnson in the earlier reply:
https://www.mql5.com/en/forum/516141#comment_60405815
Alternatively, you can manually enter https://api4.inferdeck.net in the Endpoint field under AI Assistant Options.
Hopefully this helps others who are experiencing the same connection problem.