Skip to content

feat(models): add gemini-3.6-flash, 3.5-flash-lite - #3165

Closed
smakosh wants to merge 1 commit into
mainfrom
feat/gemini-3.6-flash-flash-lite
Closed

smakosh wants to merge 1 commit into
mainfrom
feat/gemini-3.6-flash-flash-lite

Conversation

@smakosh

@smakosh smakosh commented Jul 21, 2026 •

Copy link
Copy Markdown
Member

Summary

Adds Google's two new Gemini models released 2026-07-21, both served via Google AI Studio with flex/priority service tiers:

Model Input Output Cached input Context Max output
gemini-3.6-flash $1.50/M $7.50/M $0.15/M 1,048,576 65,536
gemini-3.5-flash-lite $0.30/M $2.50/M $0.03/M 1,048,576 65,536

Both support vision, audio, PDF (document) input, tools, web search grounding ($14/1k queries), JSON output + schema, and thinking levels minimal/low/medium/high. Cache write priced at the standard $1.00/M/hr storage rate (0.08333e-6).

Notes:

  • Audio input is billed at the text rate for both models (per Google's pricing page and OpenRouter), so no separate inputAudioPrice/cachedInputAudioPrice fields — unlike gemini-3.5-flash.
  • AI Studio only for now: Google's launch post lists availability via the Gemini API; Vertex mappings can follow once availability/pricing is confirmed there.
  • chat-json passed without healStreamingJsonOutput, so the 3.5-flash AI Studio JSON-mode workaround is not needed here.

Sources: Google launch post, Gemini API pricing, OpenRouter

Testing

  • pnpm vitest run packages/models — 62/62 passed
  • TEST_MODELS="google-ai-studio/gemini-3.6-flash,google-ai-studio/gemini-3.5-flash-lite" pnpm test:e2e — 26 files / 101 tests passed against the live API, including chat-basic, streaming, tool calls (+results), JSON mode, reasoning, responses API, and response healing for both models
  • pnpm build — 17/17 tasks successful

https://claude.ai/code/session_01SYnRdQXLVyv7A2U27fnyxC

Summary by CodeRabbit

  • New Features
    • Added support for the Gemini 3.5 Flash Lite model.
    • Added support for the Gemini 3.6 Flash model.
    • Both models support multimodal capabilities, streaming, reasoning, tools, web search, and structured JSON output.

Adds Google's two new Gemini models released 2026-07-21, both served
via Google AI Studio with flex/priority service tiers:

- gemini-3.6-flash: $1.50/M in, $7.50/M out, $0.15/M cached, 1M context
- gemini-3.5-flash-lite: $0.30/M in, $2.50/M out, $0.03/M cached, 1M context

Both support vision, audio, PDF input, tools, web search, JSON output,
and thinking levels minimal/low/medium/high. Audio input is billed at
the text rate for these models, so no separate audio price fields.

Claude-Session: https://claude.ai/code/session_01SYnRdQXLVyv7A2U27fnyxC
@coderabbitai

coderabbitai Bot commented Jul 21, 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: Repository UI

Review profile: CHILL

Plan: Pro

Run ID: 7c070aa7-ee6c-4545-bf2b-7cf7c43ca422

📥 Commits

Reviewing files that changed from the base of the PR and between c95a4e0 and 2588edf.

📒 Files selected for processing (1)
  • packages/models/src/models/google.ts

Walkthrough

Adds gemini-3.5-flash-lite and gemini-3.6-flash to the Google model catalog with Google AI Studio pricing, capacity limits, reasoning configuration, supported modalities, tools, web search, and JSON output.

Changes

Gemini model catalog

Layer / File(s) Summary
Add Gemini model definitions
packages/models/src/models/google.ts
Adds provider configurations for gemini-3.5-flash-lite and gemini-3.6-flash, including pricing, context and output limits, reasoning effort levels, supported modalities, tools, web search, and JSON output.
Estimated code review effort: 1 (Trivial) ~5 minutes

Possibly related PRs

Suggested reviewers: steebchen

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Description Check ✅ Passed Check skipped - CodeRabbit’s high-level summary is enabled.
Title check ✅ Passed The title clearly summarizes the main change: adding Gemini 3.6 Flash and 3.5 Flash Lite models.
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.
✨ Finishing Touches
📝 Generate docstrings
  • Create stacked PR
  • Commit on current branch
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch feat/gemini-3.6-flash-flash-lite

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.

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.

1 participant