Skip to content

feat: add missing Gemini 3.5 Flash to Vertex AI models#433

Closed
Flayrox wants to merge 3 commits into
Zoo-Code-Org:mainfrom
Flayrox:feat/add-gemini-3.5-flash-vertex-AI
Closed

feat: add missing Gemini 3.5 Flash to Vertex AI models#433
Flayrox wants to merge 3 commits into
Zoo-Code-Org:mainfrom
Flayrox:feat/add-gemini-3.5-flash-vertex-AI

Conversation

@Flayrox

@Flayrox Flayrox commented Jun 1, 2026

Copy link
Copy Markdown

Related GitHub Issue

Closes: #

Description

This PR adds the long-awaited gemini-3.5-flash model to the Vertex AI provider configuration inside packages/types/src/providers/vertex.ts.

Key implementation details:

  • Added the correct context window (1_048_576 tokens) and max output tokens (65_535).
  • Configured the new default reasoning effort to medium along with all supported thinking levels (minimal, low, medium, high).
  • Set up the exact Priority PayGo pricing based on the latest official Google Cloud documentation ($1.50/M input tokens, $9.00/M output tokens, and $0.15/M cache read tokens).
  • Kept the configuration clean without unnecessary usage tiers as the model uses a flat pricing structure.

Test Procedure

  • Verified the TypeScript type definitions and syntax inside packages/types/src/providers/vertex.ts.
  • Manually cross-checked all technical limits and pricing structures with the official Google Cloud Vertex AI documentation.

Pre-Submission Checklist

  • Issue Linked: This PR is linked to an approved GitHub Issue (see "Related GitHub Issue" above).
  • Scope: My changes are focused on the linked issue (one major feature/fix per PR).
  • Self-Review: I have performed a thorough self-review of my code.
  • Testing: New and/or updated tests have been added to cover my changes (if applicable).
  • Documentation Impact: I have considered if my changes require documentation updates (see "Documentation Updates" section below).
  • Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Screenshots / Videos

N/A (Backend / configuration update)

Documentation Updates

  • No documentation updates are required.
  • Yes, documentation updates are required.

Additional Notes

The model config uses cacheWritesPrice: 1.50 matching the standard input token fee, following the common practice for Vertex AI models when explicit cache write costs are omitted in basic tables.

Get in Touch

Discord: Flayrox

Summary by CodeRabbit

  • New Features
    • Added support for Gemini 3.5 Flash model with 1M-context capability.
    • Model supports image inputs, prompt caching, configurable reasoning effort, and temperature tuning.
    • Pricing tiers now reflect standard and cached input/output handling.

Copilot AI review requested due to automatic review settings June 1, 2026 12:09
@coderabbitai

coderabbitai Bot commented Jun 1, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: 2afe6130-638e-4f8f-b6b5-f0fe3fd9b37d

📥 Commits

Reviewing files that changed from the base of the PR and between 276216f and 22db02d.

📒 Files selected for processing (1)
  • packages/types/src/providers/vertex.ts
🚧 Files skipped from review as they are similar to previous changes (1)
  • packages/types/src/providers/vertex.ts

📝 Walkthrough

Walkthrough

A new Vertex AI model definition for gemini-3.5-flash was added to the vertexModels map in the types package, specifying token limits, a 1,048,576 context window, supported features (images and prompt caching), reasoning configuration and temperature defaults, and pricing rates including cache read/write.

Changes

Vertex AI Model Configuration

Layer / File(s) Summary
gemini-3.5-flash model definition
packages/types/src/providers/vertex.ts
New gemini-3.5-flash entry added to vertexModels with max token counts, 1,048,576 context window, images and prompt-cache enabled, default reasoning effort and temperature support, and pricing for standard and cached input/output including cache read/write rates.

Estimated Code Review Effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Poem

A flash of gemini bright and fast,
One million tokens bound to last,
Cache and images join the play,
New model wakes to work and sway. 🐰✨

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description is mostly complete with detailed implementation details, test procedures, and a thorough pre-submission checklist. However, the issue number is missing (shows 'Closes: #' with no number), which is a required field per the template. Fill in the actual GitHub issue number in the 'Related GitHub Issue' section where it currently shows 'Closes: #'.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly and specifically describes the main change: adding the Gemini 3.5 Flash model to Vertex AI providers.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check ✅ Passed Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check ✅ Passed Check skipped because no linked issues were found for this pull request.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

Warning

There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure.

🔧 ESLint

If the error stems from missing dependencies, add them to the package.json file. For unrecoverable errors (e.g., due to private dependencies), disable the tool in the CodeRabbit configuration.

packages/types/src/providers/vertex.ts

ESLint skipped: missing config or dependency (missing-dependency). The ESLint configuration references a package that is not available in the sandbox.


Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Note

Copilot was unable to run its full agentic suite in this review.

Adds a new Vertex model entry for gemini-3.5-flash with capability flags, reasoning/temperature defaults, and pricing so it can be selected and costed like existing Gemini Vertex models.

Changes:

  • Add gemini-3.5-flash to vertexModels with limits (context/max tokens) and feature support (images, prompt cache, reasoning effort).
  • Define default reasoningEffort, defaultTemperature, and per-unit pricing fields for the new model.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread packages/types/src/providers/vertex.ts Outdated
Comment on lines +9 to +23
"gemini-3.5-flash": {
maxTokens: 65_535,
contextWindow: 1_048_576,
supportsImages: true,
supportsPromptCache: true,
supportsReasoningEffort: ["minimal", "low", "medium", "high"],
reasoningEffort: "medium",

supportsTemperature: true,
defaultTemperature: 1,
inputPrice: 1.50,
outputPrice: 9.00,
cacheReadsPrice: 0.15,
cacheWritesPrice: 1.50,
},
Comment thread packages/types/src/providers/vertex.ts Outdated
Comment thread packages/types/src/providers/vertex.ts Outdated
inputPrice: 1.50,
outputPrice: 9.00,
cacheReadsPrice: 0.15,
cacheWritesPrice: 1.50,
inputPrice: 1.50,
outputPrice: 9.00,
cacheReadsPrice: 0.15,
cacheWritesPrice: 1.50,

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

cant find this cache write price anywhere but otherwise looks good to merge

@jeanbispo

Copy link
Copy Markdown
Contributor

duplicated in #331

@navedmerchant

navedmerchant commented Jun 3, 2026

Copy link
Copy Markdown
Contributor

closing as duplicalte of #331

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants