Update default model to GPT-6.1 Sol fast - #152
Merged
Merged
Conversation
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Workspaces without a saved model selection will default to
openai/gpt-6.1-sol-fastinstead ofopenai/gpt-5.6-sol-fast. The database service test now expects the new default and still verifies that a workspace's explicit selection is honored.The live AI Gateway catalog, checked on October 2, 2026, lists the exact target slug as
openai/gpt-6.1-sol-fast(GPT-6.1 Sol (Fast)). It supports the root agent's existinglowreasoning setting. OpenAI's Fast mode documentation uses the native model IDgpt-6.1-solwithservice_tier: "fast"; Eve uses the Gateway slug above.Pricing in USD per million tokens from the Gateway catalog:
These are base rates. Above roughly 272K input tokens, the catalog's long-prompt rates are $16 input / $1.60 cached input / $60 output for the previous default and $8 / $0.40 / $30 for the new default, per million tokens. Regional processing and tool charges are separate.
Validation completed on this exact two-line change:
pnpm exec vitest run db/tests/services.test.ts— passed.pnpm check— passed, including 773 tests across 88 files.pnpm build— passed.pnpm exec eve build— passed.git diff --check— passed.Slug and pricing confirmation used the public catalog. The authenticated AI SDK catalog call was blocked by missing Gateway credentials; no live inference call was made.