feat: update defaults to latest OpenAI and Gemini models#36
Merged
montanaflynn merged 2 commits intomainfrom Apr 24, 2026
Merged
feat: update defaults to latest OpenAI and Gemini models#36montanaflynn merged 2 commits intomainfrom
montanaflynn merged 2 commits intomainfrom
Conversation
- OpenAI text: gpt-5.4 (best), gpt-5.4-mini (fast) - OpenAI image: gpt-image-2 (best) - Gemini text: gemini-3.1-pro-preview (best, replaces deprecated gemini-3-pro-preview) - Gemini image: gemini-3.1-flash-image-preview (fast, Nano Banana 2) Previous models retained as exported variables for explicit pinning. Also bumps openai-go to v3.32.0 and genai to v1.54.0, and refreshes Quick Start in README.
montanaflynn
force-pushed
the
feat/update-default-models
branch
from
e0b1b35 to
573d5f2
Compare
…, and links section
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Bumps grail's default text and image models to the latest generation across both providers. Previous defaults are kept as exported package variables so callers pinning to specific models still work.
gpt-5.4(wasgpt-5.2)gemini-3.1-pro-preview(wasgemini-3-pro-preview)gpt-5.4-mini(wasgpt-4o)gemini-3-flash-preview(unchanged)gpt-image-2(wasgpt-image-1)gemini-3-pro-image-preview(unchanged)gpt-image-1-mini(unchanged)gemini-3.1-flash-image-preview/ Nano Banana 2 (wasgemini-2.5-flash-image)Why:
gemini-3-pro-previewwas shut down 2026-03-09, so the previous Gemini Best was already broken. The OpenAI bumps adoptgpt-5.4(frontier, 1M-context, built-in computer-use) andgpt-image-2(released 2026-04-21, tops the Image Arena). Nano Banana 2 brings Pro-tier image quality at Flash speed.Other changes
openai-gov3.14 → v3.32 andgenaiv1.39 → v1.54 (needed for new model constants)..env.exampleand gitignores.envfor easier local testing.Test plan
go build ./... && go vet ./... && go test ./...— all greenexamples/model-selection/main.go --openai --gemini --imageand--text