<!-- ccr-slack-attribution -->
_Requested by **Saxon Fletcher** · [Slack
thread](https://supabase.slack.com/archives/C051L8U2EJF/p1790104861710199?thread_ts=1790104861.710199&cid=C051L8U2EJF)_
## Problem
**Before:** The Assistant's base model is `gpt-5.6-luna` at medium
reasoning effort.
**After:** The base model is `gpt-6-luna`, its direct successor, still
at medium effort. It costs half as much: $0.10/$0.50 per MTok against
$0.20/$1.20.
Resolves
[AI-1245](https://linear.app/supabase/issue/AI-1245/move-the-assistants-base-model-to-gpt-6-luna).
## Solution
This swaps `gpt-5.6-luna` for `gpt-6-luna` in
`apps/studio/lib/ai/model.utils.ts`: the model ID union, the
reasoning-support map, `ASSISTANT_MODELS`,
`DEFAULT_ASSISTANT_BASE_MODEL_ID`, and the OpenAI provider registry. The
old ID is removed, not kept next to the new one. A stored selection of
`gpt-5.6-luna` is no longer a known ID, so the client and `generate-v4`
both fall back to the new default. The eval cost table (AI-1242) and
eval experiments (AI-1243) are out of scope.
Source for the model ID and supported efforts (none/low/medium
default/high/xhigh/max): [OpenAI model docs: GPT-6
Luna](https://developers.openai.com/api/docs/models/gpt-6-luna).
`@ai-sdk/openai@4.0.41` types model IDs as a union plus `string & {}`,
so no SDK bump is needed.
## Review instructions
1. Check the diff in `model.utils.ts`. Say so if you'd rather keep
`gpt-5.6-luna` selectable as a fallback.
2. AI-1245 asks for the Assistant evals before shipping. Add the
`run-evals` label to run `braintrust-evals.yml` on this PR, or run `pnpm
--filter studio evals:run` locally. They have not been run yet because
they need OpenAI/Braintrust credentials.
3. Already run: studio `typecheck`, eslint + prettier on the changed
files, vitest for `lib/ai`, `pages/api/ai` and `state/ai-assistant` (264
passed), and `evals:preflight`.
## Checklist
- [x] I have read
[CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md)
- [x] No docs topics changed
**AI disclosure:** Claude Code wrote this PR from start to finish. Saxon
Fletcher (@SaxonF) is the accountable human and must review it before
merge.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
https://claude.ai/code/session_01W21zLTfzde6FFPyYGbGC6K
---
_Generated by [Claude
Code](https://claude.ai/code/session_01W21zLTfzde6FFPyYGbGC6K)_
Co-authored-by: Claude <noreply@anthropic.com>
