Skip to content

feat(models): add Gemini 4 Neon/Hydrogen/Carbon, GPT-6.2 Astra/Sol, GPT Image 2.6 - #10247

Merged
waleedlatif1 merged 3 commits into
stagingfrom
feat/new-models-gemini4-gpt62
Nov 20, 2026
Merged

waleedlatif1 merged 3 commits into
stagingfrom
feat/new-models-gemini4-gpt62

Conversation

@waleedlatif1

Copy link
Copy Markdown
Collaborator

Summary

  • Add gemini-4-neon, gemini-4-hydrogen, gemini-4-carbon (1,048,576 context, 65,536 default output, thinking levels per Google's thinking docs; Neon/Hydrogen accept xhigh, default high)
  • Map xhigh to the XHIGH wire value in mapToThinkingLevel (it previously fell through to HIGH); the pinned @google/genai 2.x enum predates the member
  • Add gpt-6.2-astra ($8/$0.40/$40) and gpt-6.2-sol ($2/$0.10/$10) with the >272K long-context tier (2x input/cache, 1.5x output), reasoning effort low → max
  • Add gpt-image-2.6-sunburst and gpt-image-2.6-flare to the image catalog, with xhigh/max quality like 2.5
  • Regenerate the Agent block streamed-thinking docs table

Type of Change

  • New feature

Testing

  • Pricing, limits, and thinking/effort levels checked against the official Google and OpenAI model, pricing, and guide pages, then cross-checked against the OpenRouter catalog
  • bunx vitest run providers/utils.test.ts providers/gemini providers/google lib/internal/image lib/media blocks/blocks/image_generator (395 passed)
  • bun run lint, bun run check:agent-stream-docs; type-check and audits run in CI

Checklist

  • Code follows project style guidelines
  • Self-reviewed my changes
  • Tests added/updated and passing (new tests pass the test-audit authoring gate)
  • No new warnings introduced
  • I confirm that I have read and agree to the terms outlined in the Contributor License Agreement (CLA)

@vercel

vercel Bot commented Nov 20, 2026 •

Copy link
Copy Markdown

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

1 Skipped Deployment
Project Deployment Actions Updated
docs Skipped Skipped Nov 20, 2026 7:14pm UTC

Request Review

@cubic-dev-ai cubic-dev-ai Bot 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.

All reported issues were addressed across 4 files

Reply with feedback, questions, or to request a fix.

Turn on auto-fix | Re-trigger cubic

Comment thread apps/sim/providers/google/utils.ts Resolved
@greptile-apps

greptile-apps Bot commented Nov 20, 2026 •

Copy link
Copy Markdown
Contributor

RetriggerView in GreptileConfidence Score: 5/5

[Medium impact] The PR appears safe to merge; no actionable new issues were found.

Summary

Adds Gemini 4, GPT-6.2, and GPT Image 2.6 models to the catalogs.

  • Gemini 4 Neon, Hydrogen, and Carbon join the selectable model list.
  • GPT 6.2 Astra and Sol join the selectable OpenAI model list.
  • Gemini requests send xhigh only to models that support it.
  • GPT Image 2.6 Sunburst and Flare become image-generation choices.

Reviews (2) · Last reviewed commit: "fix(models): clamp unsupported Gemini xh..." · Reviewed by Greptile

@waleedlatif1

Copy link
Copy Markdown
Collaborator Author

@greptile

@waleedlatif1

Copy link
Copy Markdown
Collaborator Author

@cubic-dev-ai review this PR

@cubic-dev-ai

cubic-dev-ai Bot commented Nov 20, 2026

Copy link
Copy Markdown
Contributor

@cubic-dev-ai review this PR

@waleedlatif1 I have started the AI code review. It will take a few minutes to complete.

@waleedlatif1
waleedlatif1 merged commit 774eed3 into staging Nov 20, 2026
62 of 63 checks passed
@waleedlatif1
waleedlatif1 deleted the feat/new-models-gemini4-gpt62 branch November 20, 2026 19:18

This branch was previously deployed

1 inactive deployment
Preview — 8b479324 Deployed Nov 20, 2026 by vercel[bot]
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