feat(models): add gemini 3.5 flash

[waleedlatif1]

Summary

• Add gemini-3.5-flash to Google and Vertex providers in models.ts
• Set as new flagship recommended: true (removed from gemini-3.1-pro-preview)
• Pricing verified from Google docs: $1.50/M input, $9.00/M output, $0.15/M cached. 1M context, thinking levels min/low/medium/high (default medium)

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)

[vercel]

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

1 Skipped Deployment

Project	Deployment	Actions	Updated (UTC)
docs	Skipped		May 19, 2026 6:12pm

[cursor]

PR Summary

Low Risk
Low risk: this is a data-only update to the static model catalog, but it changes which Gemini model is marked recommended, which may alter default suggestions/UX.

Overview
Adds new Gemini model entries for gemini-3.5-flash under both google and vertex, including pricing, 1M context window, and thinking level defaults.

Updates recommendation behavior by marking gemini-3.5-flash as recommended: true and removing recommended from gemini-3.1-pro-preview.

^{Reviewed by Cursor Bugbot for commit c8e801a. Configure here.}

[gitguardian]

️✅ There are no secrets present in this pull request anymore.

If these secrets were true positive and are still valid, we highly recommend you to revoke them.
While these secrets were previously flagged, we no longer have a reference to the
specific commits where they were detected. Once a secret has been leaked into a git
repository, you should consider it compromised, even if it was deleted immediately.
Find here more information about risks.

---

^{_{🦉 GitGuardian detects secrets in your source code to help developers and security teams secure the modern development process. You are seeing this because you or someone else with access to this repository has authorized GitGuardian to scan your pull request.}}

[greptile-apps]

Greptile Summary

Registers gemini-3.5-flash as the new recommended Gemini model in both the Google and Vertex provider definitions, with pricing, thinking-level config, and context window set. The recommended flag is moved from gemini-3.1-pro-preview to the new entry.

• gemini-3.5-flash and vertex/gemini-3.5-flash are added at the top of each provider's model list with pricing, capabilities.thinking (levels minimal/low/medium/high, default medium), maxOutputTokens: 65536 (Google only, consistent with existing Vertex pattern), and a 1M-token context window.
• recommended: true is removed from gemini-3.1-pro-preview; the Google provider's defaultModel remains gemini-2.5-pro (flagged in a previous review cycle).

Confidence Score: 5/5

Safe to merge — the change is purely additive config data in a single file with no behavioral logic.

The PR only adds two model entries (Google and Vertex) and removes one flag from an existing entry. There are no logic changes, no code paths altered, and no breaking modifications to existing models. The new entries follow the established structure used by every other model in the file.

No files require special attention.

Important Files Changed

Filename	Overview
apps/sim/providers/models.ts	Adds gemini-3.5-flash to both Google and Vertex providers with correct pricing, thinking levels, and context window; moves recommended flag from gemini-3.1-pro-preview to the new model.

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A[models.ts] --> B[google provider]
    A --> C[vertex provider]
    B --> D["gemini-3.5-flash ✨ recommended:true\ninput $1.50/M · output $9.00/M\nthinking: minimal→high · default medium\nmaxOutputTokens: 65536 · ctx 1M"]
    B --> E["gemini-3.1-pro-preview\n(recommended removed)"]
    B --> F["gemini-3.1-flash-lite-preview, gemini-3-flash-preview,\ngemini-2.5-pro, gemini-2.5-flash, ..."]
    C --> G["vertex/gemini-3.5-flash ✨\ninput $1.50/M · output $9.00/M\nthinking: minimal→high · default medium\nctx 1M"]
    C --> H["vertex/gemini-3.1-pro-preview,\nvertex/gemini-3.1-flash-lite-preview, ..."]

Loading

_{Reviews (2): Last reviewed commit: "feat(models): add gemini 3.5 flash" | Re-trigger Greptile}

[waleedlatif1]

Re: defaultModel — leaving as gemini-2.5-pro to match the existing convention. OpenAI also decouples these (defaultModel: gpt-4.1, recommended on GPT-5.5). Happy to revisit if we want to align the conventions in a follow-up.

[waleedlatif1]

@greptile

[waleedlatif1]

@cursor review

[cursor]

✅ Bugbot reviewed your changes and found no new issues!

Comment @cursor review or bugbot run to trigger another review on this PR

^{Reviewed by Cursor Bugbot for commit c8e801a. Configure here.}