Issue Station
Sign In
Tools hereToolbox

n8n - 💡(How to fix) Fix Bad request - please check your parameters. in AI agent integrated with the “Azure OpenAI Chat Model” and GPT5 [1 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
n8n-io/n8n#29780•Fetched 2026-05-06 06:35:16
View on GitHub
Comments
1
Participants
2
Timeline
6
Reactions
0
Author
kona81kona81
Participants
kona81kona81n8n-assistant[bot]n8n-assistant[bot]
Timeline (top)
labeled ×3commented ×1mentioned ×1subscribed ×1

Error Message

I am using the AI agent integrated with the “Azure OpenAI Chat Model”. When I run the workflow with GPT‑4o, I get an appropriate response, but when I change my model to GPT‑5, I start getting the following error: Between GPT‑4 and GPT‑5 the API call changes, but I am not completely sure whether the Azure OpenAI Chat Model is prepared to use GPT‑5. A call made via curl works correctly, as well as one using the HTTP Request node, but when I go through the agent I keep getting that error.

  • error: all
RAW_BUFFERClick to expand / collapse

Bug Description

I am using the AI agent integrated with the “Azure OpenAI Chat Model”. When I run the workflow with GPT‑4o, I get an appropriate response, but when I change my model to GPT‑5, I start getting the following error:

Bad request – please check your parameters The requested operation is unsupported.

Between GPT‑4 and GPT‑5 the API call changes, but I am not completely sure whether the Azure OpenAI Chat Model is prepared to use GPT‑5. A call made via curl works correctly, as well as one using the HTTP Request node, but when I go through the agent I keep getting that error.

To Reproduce

{ "parameters": { "promptType": "define", "text": "My Prompt***", "options": {} }, "type": "@n8n/n8n-nodes-langchain.agent", "typeVersion": 3.1, "position": [ 624, -32 ], "id": "0ea0040d-5274-4e4d-8916-bf7453b74025", "name": "AI Agent" }, { "parameters": { "model": "gpt-51-codex-mini", "options": {} }, "type": "@n8n/n8n-nodes-langchain.lmChatAzureOpenAi", "typeVersion": 1, "position": [ 496, 160 ], "id": "aec354b4-2cb3-4d2a-aea2-428c7b9448b4", "name": "Azure OpenAI Chat Model", "credentials": { "azureOpenAiApi": { "id": "sCLcvK55uK5dY7Z2", "name": "Azure Open AI account 2" } } },

Expected behavior

To return valid responses from agent

Debug Info

Debug info

core

  • n8nVersion: 2.17.6
  • platform: docker (self-hosted)
  • nodeJsVersion: 24.14.1
  • nodeEnv: production
  • database: postgres
  • executionMode: regular
  • concurrency: -1
  • license: community
  • consumerId: unknown

storage

  • success: all
  • error: all
  • progress: false
  • manual: true
  • binaryMode: filesystem

pruning

  • enabled: true
  • maxAge: 336 hours
  • maxCount: 10000 executions

client

  • userAgent: mozilla/5.0 (windows nt 10.0; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/146.0.0.0 safari/537.36
  • isTouchDevice: false

security

  • blockFileAccessToN8nFiles: false

Generated at: 2026-05-05T11:59:30.684Z

Operating System

Kubernetes

n8n Version

2.17.6

Node.js Version

24.14.1

Database

PostgreSQL

Execution mode

main (default)

Hosting

self hosted

extent analysis

TL;DR

The issue is likely due to the Azure OpenAI Chat Model not supporting GPT-5, and a workaround may involve using a different model or updating the model configuration.

Guidance

  • Verify that the Azure OpenAI Chat Model supports GPT-5 by checking the official documentation or contacting Azure support.
  • Try using a different model, such as GPT-4, to see if the issue persists.
  • Check the API call differences between GPT-4 and GPT-5 to ensure that the agent is configured correctly.
  • Consider using the HTTP Request node or curl to test the API call and compare the results with the agent.

Notes

The issue may be specific to the Azure OpenAI Chat Model or the n8n workflow configuration, and further investigation is needed to determine the root cause.

Recommendation

Apply workaround: Use a different model, such as GPT-4, until the Azure OpenAI Chat Model supports GPT-5 or the issue is resolved.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

To return valid responses from agent

#api#tokenizer error#prompt formatting#chain error#conversation history

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

n8n - 💡(How to fix) Fix Bad request - please check your parameters. in AI agent integrated with the “Azure OpenAI Chat Model” and GPT5 [1 comments, 2 participants]