Skip to content

docs(enterprise-api): Fast mode for GPT-6 Luna on api.blockrun.ai - #183

Merged
VickyXAI merged 2 commits into
mainfrom
docs/api-luna-fast
Nov 18, 2026
Merged

VickyXAI merged 2 commits into
mainfrom
docs/api-luna-fast

Conversation

@VickyXAI

Copy link
Copy Markdown
Contributor

Fast mode is live on api.blockrun.ai (enterprise #551, 39c60918; spec FAST-001..011, BILL-050). This adds a Fast section next to Flex in the enterprise API guide, mentions fast in the ledger's service_tier field, and adds a changelog entry. It covers 2x pricing, billing from the tier the response reports, the alias openai/gpt-6-luna-fast, the 400s, and that it's api only.

🤖 Generated with Claude Code

1bcMax added 2 commits November 18, 2026 11:50
…e, and a priority row alone is not doubled

fastGate refuses on modelRates (an absolute per-model price); a percentage
discount follows the 2x like it follows long context and Flex. BILL-050:
a call that did not ask for Fast is billed standard even if OpenAI reports
priority.
@VickyXAI
VickyXAI merged commit 6289ce4 into main Nov 18, 2026
1 check passed
@VickyXAI
VickyXAI deleted the docs/api-luna-fast branch November 18, 2026 22:47
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