Add Gemini 3.5 Flash to the model picker - #8
Merged
Conversation
The gateway exposes google/gemini-3.5-flash as a paid model with vision + thinking-mode support ($0.50/M in, $3.0/M out, 1M ctx). Listed under Reasoning — its pricing is ~30x cheaper than the Premium frontier group, and it ships with built-in thinking like O3 / Grok 4.1 Fast. Vision sibling auto-swap now considers it for image attachments routed from a Google sibling model.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Gateway already exposes
google/gemini-3.5-flash(blockrun/src/lib/models.ts:547):Adds it on the web client:
CHAT_MODELS— under the Reasoning group. Doesn't go in Premium frontier (it's ~30× cheaper than Opus 4.8) or Budget (the thinking mode is the differentiator and that's a Reasoning trait — same shelf as O3 / GPT-5.3 Codex / Grok 4.1 Fast).VISION_MODELS— added so the existingpickVisionSibling()auto-swap from a non-vision Google model picks it up when the user attaches an image.Test plan