PulseAugur
EN
LIVE 11:55:21

PayPal details Cosmos LLM Gateway for managing enterprise AI traffic

By PulseAugur Editorial · [1 sources] ·

A research paper details the design and operation of the Cosmos LLM Gateway, a system developed at PayPal to manage enterprise-wide access to multiple large language models. The gateway, built on Envoy, separates control decisions from data processing to minimize latency. It uses declarative policies evaluated by Open Policy Agent for governance, handling authentication, credential brokering, and budget evaluation. As of September 2026, the system serves over 12,000 developers and supports hundreds of business use cases, processing approximately 200 billion tokens daily across more than 100 models with high availability. AI

IMPACT Provides a blueprint for managing diverse LLM integrations and governing enterprise AI usage at scale.

RANK_REASON The cluster contains a research paper detailing a technical system. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

PayPal details Cosmos LLM Gateway for managing enterprise AI traffic

How we ranked this

Signal score
9 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster contains a research paper detailing a technical system. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
infra, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.AI TIER_1 English(EN) · Mithun Sasidharan, Srinivasan Manoharan, Rupesh Thakur, Abhinav TK, Ashwin Hegde, Anand Gautam ·

    Governing Enterprise AI Traffic at Scale: Design and Operation of a Policy-Driven, Multi-Vendor LLM Gateway on Envoy

    arXiv:2610.35509v1 Announce Type: cross Abstract: Large organizations consume large language models (LLMs) from several vendors at once, each with its own API dialect, credential model, streaming protocol and pricing. Integrated directly, this heterogeneity yields credential spra…

RELATED ENTITIES

RELATED TOPICS