Latest from Tetrate on Envoy, Istio, service mesh, and enterprise AI gateway.https://tetrate.io/https://tetrate.io/blog/attribute-based-routing-agent-router/https://tetrate.io/blog/attribute-based-routing-agent-router/Attribute-based routing is the rules-based way of smart routing in Tetrate Agent Router Enterprise. Tag requests, set ordered rules, test in monitor mode.Mon, 09 Nov 2026 08:00:00 GMThttps://tetrate.io/blog/ai-cost-attribution/https://tetrate.io/blog/ai-cost-attribution/AI cost attribution fails when tagging is optional. Require four labels at key issuance: owner, team, agent, and workload. Showback and chargeback follow.Tue, 13 Oct 2026 00:00:00 GMThttps://tetrate.io/blog/jev-directed-model-routing/https://tetrate.io/blog/jev-directed-model-routing/Choosing which model handles a task has a cost of its own. We tested Jev as a faster, cheaper way to make that decision when compared to LLMs.Wed, 30 Sep 2026 16:00:00 GMThttps://tetrate.io/blog/netscaler-cve-2026-88771-envoy-gateway/https://tetrate.io/blog/netscaler-cve-2026-88771-envoy-gateway/Citrix NetScaler zero-days CVE-2026-88771 and 88772: what a gateway in front changes, and why AI data planes need continuous patching.Tue, 29 Sep 2026 13:00:00 GMThttps://tetrate.io/blog/enabling-agentic-developers/https://tetrate.io/blog/enabling-agentic-developers/Grant providers and set team budgets once. Developers self-serve API keys and get a governed model catalog in VS Code via Tetrate Agent Router.Mon, 28 Sep 2026 04:00:00 GMThttps://tetrate.io/blog/litellm-vs-tetrate-agent-router-enterprise/https://tetrate.io/blog/litellm-vs-tetrate-agent-router-enterprise/LiteLLM vs Tetrate comparison for 2026: performance benchmarks, security and compliance gaps, total cost of ownership, plus migration paths for AI gateways.Thu, 24 Sep 2026 00:00:00 GMThttps://tetrate.io/blog/agent-router-claude-desktop/https://tetrate.io/blog/agent-router-claude-desktop/Configure Claude Desktop third-party inference to use Tetrate Agent Router. No Claude.ai account needed. One key, request logs, budgets, and model policy.Fri, 11 Sep 2026 04:00:00 GMThttps://tetrate.io/blog/agent-router-joins-aaif/https://tetrate.io/blog/agent-router-joins-aaif/Envoy AI Gateway becomes Agent Router and joins the Agentic AI Foundation: why agents need a proven, Envoy-based traffic layer, and how to get started.Thu, 10 Sep 2026 00:00:00 GMThttps://tetrate.io/blog/keeping-marketers-away-from-fable/https://tetrate.io/blog/keeping-marketers-away-from-fable/Route Claude Cowork through Agent Router Enterprise, attribute AI spend by team, and control expensive models with traffic splits, budgets, or catalog grants.Sun, 30 Aug 2026 00:00:00 GMThttps://tetrate.io/blog/how-to-report-ai-roi-to-leadership/https://tetrate.io/blog/how-to-report-ai-roi-to-leadership/Measure AI ROI for developer productivity: pick proxy metrics, pair output with inference spend, and use a gateway so cost data is complete.Thu, 20 Aug 2026 07:00:00 GMThttps://tetrate.io/blog/tetrate-model-provider-vscode-extension/https://tetrate.io/blog/tetrate-model-provider-vscode-extension/Use 164 AI models in VS Code with one Agent Router API key. A language model provider for chat, agent mode, and vscode.lm—not just BYOK chat.Wed, 12 Aug 2026 04:00:00 GMThttps://tetrate.io/blog/sovereign-ai-cost-control-point/https://tetrate.io/blog/sovereign-ai-cost-control-point/A distributed AI gateway answers who spent and where traffic ran. The savings it recovers can fund a sovereign AI program.Mon, 03 Aug 2026 00:00:00 GMThttps://tetrate.io/blog/token-optimization-ai-token-costs/https://tetrate.io/blog/token-optimization-ai-token-costs/Track AI token spend by team, set budgets that hold, and decide who needs a Claude Code subscription, from one AI gateway.Sat, 25 Jul 2026 00:00:00 GMThttps://tetrate.io/blog/run-your-own-kimi-k3-sovereign-ai/https://tetrate.io/blog/run-your-own-kimi-k3-sovereign-ai/Kimi K3 is the largest open-weight model ever shipped. What it takes to serve it in your perimeter, and route it with Agent Router Enterprise.Tue, 21 Jul 2026 00:00:00 GMThttps://tetrate.io/blog/doubling-envoy-throughput-on-nvidia-bluefield-3/https://tetrate.io/blog/doubling-envoy-throughput-on-nvidia-bluefield-3/We modified Envoy to offload TLS cryptography to NVIDIA BlueField-3 hardware accelerators. On a single core with AES-256 and a 5 MB payload, throughput went from 6.6 Gbps to 13.6 Gbps — 2x, without touching L7 policy.Mon, 20 Jul 2026 16:00:00 GMThttps://tetrate.io/blog/tetrate-vs-openrouter/https://tetrate.io/blog/tetrate-vs-openrouter/OpenRouter helps developers access and evaluate models. Tetrate helps enterprises operate AI traffic at scale.Mon, 20 Jul 2026 00:00:00 GMThttps://tetrate.io/blog/envoy-ai-gateway-latency-benchmark/https://tetrate.io/blog/envoy-ai-gateway-latency-benchmark/Independent Broadcom benchmark: Envoy AI Gateway adds ~2 ms latency under enterprise LLM load — Tetrate Agent Router Enterprise data plane.Thu, 16 Jul 2026 00:00:00 GMThttps://tetrate.io/blog/token-brokering-ai-agent-cost-control/https://tetrate.io/blog/token-brokering-ai-agent-cost-control/Token brokering enforces AI cost budgets in the request path—when spend crosses a budget, Agent Router falls back to a cheaper approved model.Wed, 15 Jul 2026 00:00:00 GMThttps://tetrate.io/blog/ai-gateway-meta-provider-agent-harness/https://tetrate.io/blog/ai-gateway-meta-provider-agent-harness/Why agent harnesses need an AI gateway as the meta-provider: model routing, MCP tool governance, guardrails, and telemetry beneath your harness.Sat, 04 Jul 2026 00:00:00 GMThttps://tetrate.io/blog/envoy-waf-performance-benchmarks/https://tetrate.io/blog/envoy-waf-performance-benchmarks/We benchmarked three Envoy WAF flavors. The engine overhead is minimal — the cost is in the rules you load — and full OWASP CRS body inspection is production-viable with the right build.Thu, 02 Jul 2026 00:00:00 GMThttps://tetrate.io/blog/enterprise-ai-gateway-agent-router/https://tetrate.io/blog/enterprise-ai-gateway-agent-router/An AI gateway — also called an LLM gateway — is where teams control AI cost, routing, caching, and governance. Why your bill is a gateway problem.Sun, 28 Jun 2026 00:00:00 GMThttps://tetrate.io/blog/envoy-ai-gateway-v1-0-release/https://tetrate.io/blog/envoy-ai-gateway-v1-0-release/Envoy AI Gateway 1.0 is generally available: the first stable, production-ready release of the open source AI gateway built on CNCF's Envoy Gateway.Tue, 23 Jun 2026 00:00:00 GMThttps://tetrate.io/blog/boe-v061/https://tetrate.io/blog/boe-v061/Built On Envoy v0.6.1 brings two new extensions contributed by Palantir Technologies and ships a new Web UI that makes the developer experience faster and easier than ever.Thu, 18 Jun 2026 00:00:00 GMThttps://tetrate.io/blog/mcp-without-the-sprawl/https://tetrate.io/blog/mcp-without-the-sprawl/MCP is winning, the governance story isn't. Five things that break when regulated enterprises adopt MCP — and what a single governed boundary fixes.Tue, 16 Jun 2026 16:00:00 GMThttps://tetrate.io/blog/solve-llm-provider-lock-in/https://tetrate.io/blog/solve-llm-provider-lock-in/An AI gateway centralizes model routing, fallback, cost control, and observability to solve provider lock-in, outages, and runaway LLM costs at scale.Tue, 09 Jun 2026 04:00:00 GMT