{"slug": "cost-governed-rag-unified-per-tenant-cost-attribution-across-retrieval-and-in", "title": "Cost-Governed RAG: Unified Per-Tenant Cost Attribution Across Retrieval and Generation in Multi-Tenant LLM Systems", "summary": "Researchers introduced Cost-Governed RAG, an architecture integrating a codebook-oblivious vector index with a multi-tenant LLM governance gateway to achieve per-tenant cost attribution across retrieval and generation in enterprise RAG systems. Deployed on Snowpark Container Services, it achieved 99.96% cost attribution accuracy across 100 simulated tenants while reducing retrieval infrastructure cost by 3.1-9.0x compared to managed vector database services.", "body_md": "arXiv:2607.12188v1 Announce Type: new\nAbstract: Enterprise Retrieval-Augmented Generation (RAG) deployments face a critical governance gap: while LLM generation cost is metered per token, the retrieval layer - vector memory, similarity compute, and embedding API calls - remains an unattributed shared cost, enabling invisible cross-subsidization among tenants. We present Cost-Governed RAG, an architecture that integrates a codebook-oblivious vector index (TurboVec) with a multi-tenant LLM governance gateway, creating a unified observability stack where embedding, retrieval, and generation costs are jointly attributable per tenant. The architecture exploits TurboVec's deterministic, closed-form memory formula to enable near-exact per-tenant retrieval cost calculation - a property unavailable in graph-based indexes with non-linear memory overhead. Deployed on Snowpark Container Services within a cloud data platform's governance boundary, the system achieves 99.96% end-to-end cost attribution accuracy across 100 simulated tenants (10M vectors, log-normal size distribution) with telemetry overhead below 0.04% of query latency. The architecture reduces retrieval infrastructure cost by 3.1-9.0x compared to managed vector database services under the pricing assumptions detailed in Section IV. We formalize a three-layer cost model and demonstrate that codebook-oblivious quantization enables deterministic per-tenant cost attribution while also removing the shared-codebook leakage surface present in trained quantizers - the latter observation being exploratory and subject to the limitations described in Section VII.", "url": "https://wpnews.pro/news/cost-governed-rag-unified-per-tenant-cost-attribution-across-retrieval-and-in", "canonical_source": "https://arxiv.org/abs/2607.12188", "published_at": "2026-07-15 04:00:00+00:00", "updated_at": "2026-07-15 04:22:55.179518+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "ai-infrastructure"], "entities": ["TurboVec", "Snowpark Container Services", "arXiv"], "alternates": {"html": "https://wpnews.pro/news/cost-governed-rag-unified-per-tenant-cost-attribution-across-retrieval-and-in", "markdown": "https://wpnews.pro/news/cost-governed-rag-unified-per-tenant-cost-attribution-across-retrieval-and-in.md", "text": "https://wpnews.pro/news/cost-governed-rag-unified-per-tenant-cost-attribution-across-retrieval-and-in.txt", "jsonld": "https://wpnews.pro/news/cost-governed-rag-unified-per-tenant-cost-attribution-across-retrieval-and-in.jsonld"}}