feat(models): add gpt-5.4-mini and gpt-5.4-nano

[waleedlatif1]

Summary

• Add gpt-5.4-mini and gpt-5.4-nano model definitions (openai + azure)
• Pricing, context window, reasoning effort, and verbosity configured per OpenAI docs

Type of Change

• New feature

Testing

Tested manually

Checklist

• Code follows project style guidelines
• Self-reviewed my changes
• Tests added/updated and passing
• No new warnings introduced
• I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

[cursor]

PR Summary

Low Risk
Low risk metadata-only change, but it can affect model selection and any UI/cost calculations that rely on these IDs and pricing values.

Overview
Adds new model definitions for gpt-5.4-mini and gpt-5.4-nano under both openai and azure-openai in apps/sim/providers/models.ts.

Each new entry includes updated pricing (including cached input), a 400000 context window, and declares support for reasoningEffort, verbosity, and maxOutputTokens.

^{Written by Cursor Bugbot for commit 059b9c3. Configure here.}

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

1 Skipped Deployment

Project	Deployment	Actions	Updated (UTC)
docs	Skipped		Mar 31, 2026 11:25pm

[greptile-apps]

Greptile Summary

This PR adds gpt-5.4-mini and gpt-5.4-nano model definitions to both the openai and azure-openai provider sections in apps/sim/providers/models.ts. The additions are well-structured and consistent with the existing gpt-5.4 family patterns.

• Both models are added to both openai and azure-openai providers (as gpt-5.4-mini/gpt-5.4-nano and azure/gpt-5.4-mini/azure/gpt-5.4-nano respectively)
• Capabilities mirror the full gpt-5.4 baseline: reasoningEffort with ['none', 'low', 'medium', 'high', 'xhigh'], verbosity with ['low', 'medium', 'high'], and maxOutputTokens: 128000
• Context window is 400000 tokens, matching other smaller gpt-5.x models (gpt-5.2, gpt-5.1, gpt-5)
• Cached input discount is consistently 10% of the base input price across both models
• Models are inserted in the correct position within the model list (after gpt-5.4-pro, before gpt-5.2)

Confidence Score: 5/5

This PR is safe to merge — it adds two new model definitions with no logic changes and no breaking modifications to existing entries.

All changes are additive, follow the established pattern exactly, and are mirrored consistently across both openai and azure-openai providers. No custom instruction violations, no logic changes, no test coverage needed for static config data.

No files require special attention.

Important Files Changed

Filename	Overview
apps/sim/providers/models.ts	Adds gpt-5.4-mini and gpt-5.4-nano definitions for both OpenAI and Azure providers with consistent pricing, capabilities (reasoningEffort + verbosity), maxOutputTokens, and contextWindow values.

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A[PROVIDER_DEFINITIONS] --> B[openai]
    A --> C[azure-openai]

    B --> D[gpt-5.4]
    B --> E[gpt-5.4-pro]
    B --> F["gpt-5.4-mini NEW"]
    B --> G["gpt-5.4-nano NEW"]
    B --> H[gpt-5.2]

    C --> I[azure/gpt-5.4]
    C --> J["azure/gpt-5.4-mini NEW"]
    C --> K["azure/gpt-5.4-nano NEW"]
    C --> L[azure/gpt-5.2]

    F --> M["contextWindow: 400k\ninput: $0.75/M\noutput: $4.5/M\ncachedInput: $0.075/M"]
    G --> N["contextWindow: 400k\ninput: $0.20/M\noutput: $1.25/M\ncachedInput: $0.02/M"]

Loading

_{Reviews (2): Last reviewed commit: "feat(models): add gpt-5.4-mini and gpt-5..." | Re-trigger Greptile}

[waleedlatif1]

@greptile

[waleedlatif1]

@cursor review

[cursor]

Cursor Bugbot has reviewed your changes and found 1 potential issue.

^{Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.}