Requesty

@RequestyAI

The AI gateway. One API for 600+ models, routed intelligently. Built for teams shipping AI to production.

Pinned
Requesty
@RequestyAI
Jul 24
Claude Opus 5 is live on Requesty. Day-0 launch partner! Early internal tests: frontier quality, noticeably more cost-efficient, plus new mid-conversation tool changes for leaner token use on long runs. Same price as Opus 4.8: $5/M in, $25/M out. Point at
00:00
10
Requesty
@RequestyAI
53m
Gemini 3.8 Flash from @GoogleDeepMind is now available on Requesty! Improvements across the board from Gemini 3.7 Flash at the same price: > Input $0.750/M > Cached Input: $0.075/M > Output: $3.75/M Try it here: app.requesty.ai/model-library?…
Requesty
@RequestyAI
22h
Fable 5.1 now live on Requesty!
Requesty
@RequestyAI
Sep 1
Compliance on LLM traffic isn't a policy doc. It's a config. On Requesty you can: → Enforce zero data retention on every request body → Pin serving to EU-only gateways → Mask and report PII + secrets in flight → Route only to ZDR model endpoints Set it once. It holds on
Requesty
@RequestyAI
Sep 1
We've partnered with @runware to bring their inference endpoints to Requesty! Access GLM 5.3 Flash, DeepSeek v4 Flash 0731 and more. Try them here: app.requesty.ai/model-library?…