The latest features, improvements, and fixes across LLM Gateway, DevPass, Lounge, and Airside.
Video Studio in Lounge now runs FLUX 3 Max on fal, KLING v3.0 Pro, Gemini Omni 1.1 Flash, VEED Fabric 1.0, MiniMax H3 Max and Grok Imagine Video 1.5 Lite, from 2-cent-per-second drafts to 1080p shots with sound and lip-synced talking video. Finished videos now show up the moment they are ready, without a reload.
Read more about Six New Video Models in Lounge →
Lounge gets a Decision Studio: paste any text or image, build yes/no, pick-one and rating questions in the browser, and run them on GPT-6 Luna Decisions, Microsoft-Decision-1 or Jev. Answers come back as probabilities you can read at a glance, compare across models, and copy as a ready-to-send /v1/decisions request.
Read more about Decision Studio in Lounge →
Airworthy (standard AW-1) is a certificate for inference providers on Airside. LLM Gateway checks each carrier's claims on training, prompt logging, retention, legal entity, headquarters and audits against contracts, registries and audit reports, then stamps the provider page with exactly what was verified.
Read more about Airside: Airworthy Certification →
Manage every API key in your organization from one page, deactivate, reactivate, or delete keys in bulk, see usage for the last 24 hours to 90 days, get warned about keys that have not been used in 30 or 90 days, and cap low-use keys with a one-click spend limit suggestion.
Read more about Bulk API Key Management and Insights →
The new /v1/decisions endpoint follows OpenAI's Decisions API and serves every decision model through one request shape. GPT-6 Luna Decisions launches there with image input at $0.10 per million input tokens, Microsoft-Decision-1 joins via Azure at $0.042, Jev moves over at the same price, and /v1/systemone will be deprecated soon.
Read more about OpenAI-Compatible Decisions API →
Retain All Data is now an Enterprise feature. New organizations are Metadata Only, and existing organizations that retain full payloads keep the setting until November 8, 2026. Usage analytics and the Responses API are unchanged.
Read more about Full Data Retention Moves to Enterprise →
Call Perplexity's standalone Search API through LLM Gateway at /v1/search. It returns ranked web results with extracted page snippets instead of a model-written answer, billed per request, with failed requests free.
Read more about Perplexity Search API →
Request Azure's low-latency Priority tier with the same service_tier field you already use for OpenAI. The gateway reads back the tier Azure actually served, so a request Microsoft downgrades is billed at standard rates rather than the premium you asked for.
Read more about Azure Priority Processing →
A new `smart` model string: choose which models it may resolve to, and let a classifier rate each request so easy prompts go to a cheap model and hard ones go to a frontier model. Existing `auto` behaviour is unchanged. Available to every organization while in beta; not available on DevPass yet.
Read more about Smart Routing →
End-users who buy credits in your app now get a receipt led by your brand, with your support address and a card statement that reads LLMGTWY* YOURBRAND instead of ours. Refunds send a matching credit note. Available on Payments SDK projects, which are in preview.
Read more about Branded Payments SDK Receipts →
Showing 10 of 115 updates
Load more