fix(OpenAI Node): Replace hardcoded models with RLC

[michael-radency]

Summary

PR replaces hardcoded models with RLC parameter, fixes bugs with gpt-image other then gpt-image-1

Related Linear tickets, Github issues, and Community forum posts

https://linear.app/n8n/issue/NODE-4791/openai-updates-for-ai-gateway

Review / Merge checklist

• PR title and summary are descriptive. (conventions)
• Docs updated or follow-up ticket created.
• Tests included.
• PR Labeled with Backport to Beta, Backport to Stable, or Backport to v1 (if the PR is an urgent fix that needs to be backported)
• I have seen this code, I have run this code, and I take responsibility for this code.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!

[cubic-dev-ai]

No issues found across 6 files

Architecture diagram

sequenceDiagram
    participant UI as n8n UI (Client)
    participant Node as OpenAI Node (v2.2)
    participant Method as listSearch.ts
    participant API as OpenAI API
    participant Helper as Binary Helper

    Note over UI,API: Resource Selection (Design Time)
    UI->>Method: NEW: Request available image models
    Method->>API: GET /v1/models
    API-->>Method: Returns all model IDs
    Method->>Method: NEW: Filter for IDs including "dall-e" or "gpt-image"
    Method-->>UI: Return filtered list (RLC)

    Note over UI,API: Node Execution (Runtime)
    UI->>Node: Execute "Generate" action
    
    Node->>Node: Check NodeType version (>= 2.2)
    alt NEW: Node Version is 2.2+
        Node->>Node: Extract value from RLC model parameter
    else Legacy Version
        Node->>Node: Read static model parameter
    end

    Node->>Node: CHANGED: Check if model name starts with "gpt-image"
    
    alt Model is "gpt-image-*"
        Node->>Node: CHANGED: Disable response_format parameter
        Note right of Node: Fixes support for gpt-image-1-mini, etc.
    else Model is "dall-e-*"
        Node->>Node: Set response_format (url or b64_json)
    end

    Node->>Node: CHANGED: Map "dalleQuality" option to "quality" field
    
    Node->>API: POST /v1/images/generations (Body with model & prompt)
    API-->>Node: Image data (URL or Base64)

    alt NEW/CHANGED: Process gpt-image result (Binary only)
        Node->>Helper: prepareBinaryData(base64)
        Helper-->>Node: Binary property
    else Process dall-e result
        alt returnImageUrls is true
            Node->>Node: Return JSON with URL
        else Default
            Node->>Helper: prepareBinaryData(base64)
            Helper-->>Node: Binary property
        end
    end

    Node-->>UI: Output Execution Data (Binary or JSON)

Loading

[alexander-gekov]

only other model I think we can add is chatgpt-image-latest

[alexander-gekov]

lgtm

[github-actions]

Performance Comparison

Comparing current → latest master → 14-day baseline

PR perf tests not yet enabled. Current = latest master run.

Idle baseline with Instance AI module loaded

Metric	Current	Latest Master	Baseline (avg)	vs Master	vs Baseline	Status
instance-ai-heap-used-baseline	186.88 MB	186.88 MB	186.42 MB (σ 0.27)	+0.0%	+0.2%	⚠️
instance-ai-rss-baseline	386.52 MB	386.52 MB	364.63 MB (σ 22.57)	+0.0%	+6.0%	✅

docker-stats

Metric	Current	Latest Master	Baseline (avg)	vs Master	vs Baseline	Status
docker-image-size-n8n	1269.76 MB	1269.76 MB	1269.76 MB (σ 0.00)	+0.0%	+0.0%	—
docker-image-size-runners	386.00 MB	386.00 MB	390.33 MB (σ 9.21)	+0.0%	-1.1%	✅

Memory consumption baseline with starter plan resources

Metric	Current	Latest Master	Baseline (avg)	vs Master	vs Baseline	Status
memory-rss-baseline	288.44 MB	288.44 MB	290.51 MB (σ 41.09)	+0.0%	-0.7%	✅
memory-heap-used-baseline	114.39 MB	114.39 MB	114.37 MB (σ 0.40)	+0.0%	+0.0%	✅

How to read this table

• Current: This PR's value (or latest master if PR perf tests haven't run)
• Latest Master: Most recent nightly master measurement
• Baseline: Rolling 14-day average from master
• vs Master: PR impact (current vs latest master)
• vs Baseline: Drift from baseline (current vs rolling avg)
• Status: ✅ within 1σ | ⚠️ 1-2σ | 🔴 >2σ regression

[codecov]

Bundle Report

Changes will increase total bundle size by 148 bytes (0.0%) ⬆️. This is within the configured threshold ✅

Detailed changes

Bundle name	Size	Change
editor-ui-esm	45.76MB	148 bytes (0.0%) ⬆️

Affected Assets, Files, and Routes:

view changes for bundle: editor-ui-esm

Assets Changed:

Asset Name	Size Change	Total Size	Change (%)
assets/worker-*.js	3.15MB	3.17MB	17586.03% ⚠️
assets/worker-*.js	-3.15MB	17.9kB	-99.43%
assets/constants-*.js	148 bytes	3.14MB	0.0%

[n8n-assistant]

Got released with n8n@2.18.0