# LiteLLM blog

> Every post on https://docs.litellm.ai/blog, newest first. Append `.md` to any post URL for its markdown. RSS: https://docs.litellm.ai/blog/rss.xml

- [Decision models on LiteLLM: /v1/decisions and /v1/systemone](https://docs.litellm.ai/blog/decision-models.md) (2026-10-14): Decision models return probabilities instead of text, which makes routing, triage and guardrail checks cheap and deterministic. LiteLLM serves nine providers...
- [Workshop: Build a self-hosted cloud agent.](https://docs.litellm.ai/blog/cloud-agent-workshop.md) (2026-10-13): Build a self-hosted cloud agent with the LiteLLM team. A two-week remote workshop, October 19–30, to build a working v0 and deploy an internal beta on your...
- [Gemini 4 Argon API Pricing and Day 0 Support on LiteLLM](https://docs.litellm.ai/blog/gemini-4-argon.md) (2026-10-13): Gemini 4 Argon costs $2.00 per 1M input tokens and $10.00 per 1M output tokens until Nov 30. LiteLLM supports it on day 0 on AI Studio and Google Cloud.
- [October Townhall: Product + Roadmap Updates](https://docs.litellm.ai/blog/october-townhall-announcement.md) (2026-10-10): Join the LiteLLM October townhall on Thursday, 22 October at 7:30 AM PT to learn about LiteLLM's product updates and roadmap.
- [Introducing Microsoft 365 Copilot in LiteLLM](https://docs.litellm.ai/blog/microsoft-365-copilot.md) (2026-10-09): Use Microsoft 365 Copilot from your applications through LiteLLM, with access to your Microsoft 365 work data.
- [Introducing litellm-core: the first step toward a leaner SDK](https://docs.litellm.ai/blog/introducing-litellm-core.md) (2026-10-08): Ongoing work to reduce LiteLLM's dependencies and installation footprint, improve runtime loading, and make imports faster
- [Claude Haiku 5.5 API Pricing and Day 0 Support on LiteLLM](https://docs.litellm.ai/blog/claude-haiku-5-5.md) (2026-10-07): Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens. LiteLLM supports it on day 0 on Anthropic, AWS, Google Cloud and Azure.
- [Open Sourcing Moyai: Self-Hosted Cloud Coding Agent](https://docs.litellm.ai/blog/moyai-open-source.md) (2026-10-07): Run cloud coding agents on your own infrastructure with Moyai. Choose your agent and models through LiteLLM, track costs, and follow the setup guide.
- [Day 0 Support: Nano Banana 2.1](https://docs.litellm.ai/blog/nano_banana_2_1.md) (2026-10-06): Day 0 support for Gemini Nano Banana 2.1 on LiteLLM, on Google AI Studio and Gemini Enterprise Agent Platform, with image output at half Nano Banana 2's price.
- [How LiteLLM Lens finds repeated failures across 1,000s of agent traces](https://docs.litellm.ai/blog/lens-failure-patterns.md) (2026-10-05): Inside Lens: parallel trace review, Python tools for large traces, and investigations that connect repeated failures to source evidence.
- [How we cut time to first byte by 94% for long prompts](https://docs.litellm.ai/blog/long-prompt-latency.md) (2026-10-03): A 440k-token benchmark went from 553 ms to 35 ms median time to first byte. We removed unnecessary prompt-cache routing work before the model call.
- [How we built our own internal Devin in 2 days](https://docs.litellm.ai/blog/internal-devin-two-days.md) (2026-10-03): How we built Moyai Devin with Render, Modal, Hermes, Temporal, and LiteLLM: durable sessions, parallel agents, Slack, and shared organization connections.
- [Adding Self-hosted Auto Router Classifiers: Laya & Nimble](https://docs.litellm.ai/blog/laya-nimble-classifiers.md) (2026-10-02): Use Laya or Bespoke Nimble to classify Auto Router requests on your own infrastructure. Control where classification runs, which model you serve, and how you...
- [Launching LiteLLM Lens](https://docs.litellm.ai/blog/litellm-lens-launch.md) (2026-10-01): LiteLLM Lens turns the traces flowing through your gateway into findings your agents can act on. Built for agent swarms generating 200K+ traces.
- [How we cut LiteLLM's Redis round trips per request by 64%](https://docs.litellm.ai/blog/redis-request-pipelines.md) (2026-10-01): A governed request to the LiteLLM AI Gateway waited on Redis 22 times. It now waits 8 times: one pipeline per Redis backend before the model call, one after.
- [How we made the LiteLLM Usage page 120x faster](https://docs.litellm.ai/blog/usage-page-bounded-loading.md) (2026-09-30): From six minutes to 3.2 seconds: how moving aggregation into Postgres made LiteLLM's Usage page roughly 120x faster in our benchmark.
- [Day 0 Support: GPT-6.1 Sol](https://docs.litellm.ai/blog/gpt_6_1_sol.md) (2026-09-29): Day 0 support for GPT-6.1 Sol on LiteLLM, with cached input at half GPT-6 Sol's price.
- [Learn the LiteLLM gateway with a guided course](https://docs.litellm.ai/blog/litellm-gateway-course.md) (2026-09-28): Follow a request through the LiteLLM gateway, Router, and SDK. A guided course for teams deploying the gateway and contributors making code changes.
- [Day 0 Support: Claude Sonnet 5.5](https://docs.litellm.ai/blog/claude_sonnet_5_5.md) (2026-09-28): Day 0 support for Claude Sonnet 5.5 on the LiteLLM AI Gateway. Use it across Anthropic, Bedrock, Gemini Enterprise Agent Platform, and Azure.
- [Introducing the LiteLLM ROI Calculator](https://docs.litellm.ai/blog/litellm-roi-calculator.md) (2026-09-26): Compare each engineer's LiteLLM gateway spend with the estimated effort of their merged pull requests. Open source and self-hosted.
- [Introducing LiteAgents](https://docs.litellm.ai/blog/liteagents-sdk.md) (2026-09-25): Switch agent harnesses without rewriting your agent. Keep your tools and model configuration, use native harness controls, and add Temporal when you need...
- [September Townhall Updates: 583 Bug Fixes, OCR on Rust, and 83.5% Coverage](https://docs.litellm.ai/blog/september-townhall-updates.md) (2026-09-24): A recap of the September LiteLLM town hall: security and stability updates, OCR running on Rust by default, test coverage past the 80% target, and new Fusion...
- [Day 0 support: Gemini 3.8 Flash TTS and Flash-Lite TTS](https://docs.litellm.ai/blog/gemini_3_8_flash_tts.md) (2026-09-23): Day 0 support for Gemini 3.8 Flash TTS and Flash-Lite TTS on LiteLLM's /v1/audio/speech, with launch pricing tracked through 2026.
- [Introducing LiteAdmin MCP](https://docs.litellm.ai/blog/litellm-admin-mcp.md) (2026-09-23): Give your agent tools to create keys, add models, and manage budgets with LiteAdmin MCP. Use the same connector through LiteAdmin, our Slack admin agent.
- [Day 0 Support: GPT-6 Sol and GPT-6 Luna](https://docs.litellm.ai/blog/gpt_6_sol_luna.md) (2026-09-22): Day 0 support for GPT-6 Sol and GPT-6 Luna on LiteLLM, at half the price of their GPT-5.6 counterparts.
- [Day 0 Support: Claude Opus 5.5](https://docs.litellm.ai/blog/claude_opus_5_5.md) (2026-09-22): Day 0 support for Claude Opus 5.5 on the LiteLLM AI Gateway. Use it across Anthropic, Bedrock, Gemini Enterprise Agent Platform, and Azure.
- [Getting Started with Fireworks AI on LiteLLM](https://docs.litellm.ai/blog/fireworks-getting-started.md) (2026-09-22): A beginner tutorial: run an open model on Fireworks AI behind a LiteLLM gateway, call it with the OpenAI SDK you already use, then add a second model and a...
- [Day 0 Support: Xiaomi MiMo V2.6](https://docs.litellm.ai/blog/mimo_v2_6.md) (2026-09-22): Day 0 support for Xiaomi MiMo V2.6 Pro and Flash on LiteLLM, priced on the native route for the first time.
- [Claude Code server-side auto mode through LiteLLM](https://docs.litellm.ai/blog/claude-code-server-side-auto-mode.md) (2026-09-21): Anthropic is moving Claude Code auto mode's safety classifier server-side. LiteLLM's native /v1/messages route now forwards the safeguards contract to the...
- [Day 0 Support: Grok 4.7](https://docs.litellm.ai/blog/grok_4_7.md) (2026-09-21): Day 0 support for Grok 4.7 on LiteLLM, at the same price as Grok 4.6.
- [JEV Classifier: 5.43x as Fast as Haiku, 96% Lower Cost](https://docs.litellm.ai/blog/jev-auto-router-benchmark.md) (2026-09-20): JEV classified requests 5.43x as fast as Haiku by median latency in our AI Gateway benchmark. Explore the setup, cost savings and methodology.
- [TypeSafe Jev on LiteLLM](https://docs.litellm.ai/blog/typesafe_jev.md) (2026-09-20): TypeSafe AI's Jev lands in LiteLLM v1.103.0-rc: call it through the proxy with logging and cost tracking.
- [Auto-Router: Switching Tiers Without Encrypted Content Failures](https://docs.litellm.ai/blog/auto-router-encrypted-content-routing.md) (2026-09-18): How LiteLLM safely removes undecryptable encrypted reasoning from cross-tier follow-ups so Auto-Router can keep routing requests
- [Day 0 Support: Qwen3.8-Omni-Flash](https://docs.litellm.ai/blog/qwen3_8_omni_flash.md) (2026-09-18): Day 0 support for Qwen3.8-Omni-Flash on LiteLLM, with text, image, audio and video input.
- [Reduce agent context with TypeSafe Jev and LiteLLM](https://docs.litellm.ai/blog/typesafe-jev-compaction.md) (2026-09-18): Use TypeSafe Jev to remove old tool results from bot conversations and enable compaction for a team in LiteLLM.
- [Auto Router: 5 Improvements for Cost, Speed, and Team Control](https://docs.litellm.ai/blog/auto-router-five-improvements.md) (2026-09-17): Five Auto Router updates: cache-cost estimates, Fast Mode by tier, team-managed routers, live CLI stats, and more accurate Anthropic savings.
- [September Townhall: Product + Roadmap Updates](https://docs.litellm.ai/blog/september-townhall-announcement.md) (2026-09-16): Join the LiteLLM September townhall on Thursday, 24 September at 7:30 AM PT to learn about LiteLLM's product updates and roadmap.
- [Auto Router: Maximize Quality & Savings with Our Fuse LLM Classifier](https://docs.litellm.ai/blog/auto-router-fuse-v2.md) (2026-09-14): We’re improving Fuse V2 by combining complexity and capability assessment to learn where each model succeeds, fails, and needs an upgrade.
- [OCR uses Rust by default starting with v1.102.0-rc.1](https://docs.litellm.ai/blog/litellm-rust-ocr.md) (2026-09-13): Starting with v1.102.0-rc.1, OCR calls use the Rust implementation by default while preserving the existing API.
- [Incident Report: Retry Breadcrumb Memory Growth Causing OOM on v1.100.0](https://docs.litellm.ai/blog/retry-breadcrumb-oom-incident.md) (2026-09-12): Date: September 7 to September 9, 2026
- [Auto Router: 45% Lower Cost on 25 SWE-bench Tasks](https://docs.litellm.ai/blog/auto-router-capability-benchmark.md) (2026-09-11): We solved 23 of 25 SWE-bench Verified tasks with LiteLLM's experimental capability router for $11.15, compared with $20.27 using Opus 5.
- [How Pfizer Improved LiteLLM Gateway Performance and Resiliency at Scale](https://docs.litellm.ai/blog/pfizer-gateway-performance-and-resiliency.md) (2026-09-11): How Pfizer AI Platform Engineering isolated a Redis connection handling bug that cut LiteLLM gateway throughput by ~48% with zero HTTP errors, reduced CI...
- [Auto-Router Updates: Harness-Aware Routing](https://docs.litellm.ai/blog/auto-router-harness-aware-classification.md) (2026-09-10): Harness-aware Auto-Router updates for Claude Code and Codex: less classifier context, encrypted task support, and clearer routing logs.
- [Secure shared AI agents with identity-aware access and spend controls](https://docs.litellm.ai/blog/ai-gateway-identity-and-finops.md) (2026-09-08): How LiteLLM preserves caller identity across shared agents, governs model and MCP access, and enforces independent budgets for each business unit.
- [AutoRouter: Tune Heuristics for Your Traffic](https://docs.litellm.ai/blog/auto-router-heuristic-tuning.md) (2026-09-08): Tune AutoRouter heuristic dimensions for specific workloads, improve classification accuracy, and configure tiers from models you already serve.
- [Our Updated SOC 2 Type 2 Report Is Available](https://docs.litellm.ai/blog/soc2-type-2-report.md) (2026-09-08): LiteLLM's updated SOC 2 Type 2 report is now available through the LiteLLM Trust Center.
- [Subtask-Specific Routing: Same Quality, 46% Less Cost](https://docs.litellm.ai/blog/subtask-type-routing.md) (2026-09-07): Routing each agent turn by what the agent is doing, exploring, implementing, or verifying, instead of by how hard the prompt looks. On a SWE-bench Verified...
- [AutoRouter Per-Hop Compression: Cut LLM Classifier Costs Another 32%](https://docs.litellm.ai/blog/auto-router-per-hop-compression.md) (2026-09-05): The complexity router's LLM classifier can now use different compression than the model call it routes to. The classifier only needs enough context to route...
- [Auto-Router: Escalate a Task That Gets Stuck](https://docs.litellm.ai/blog/auto-router-stall-escalation.md) (2026-09-04): The Auto-Router now reads the assistant's own recent tool calls, notices when an agentic task is stuck in a retry loop, and escalates it one tier...
- [Day 0 Support: GPT-6 Astra](https://docs.litellm.ai/blog/gpt_6_astra.md) (2026-09-03): Day 0 support for OpenAI's GPT-6 Astra on LiteLLM, with pricing, reasoning params, and the Responses API bridge.
- [Day 0 support: Meta Muse Spark 1.3](https://docs.litellm.ai/blog/muse_spark_1_3.md) (2026-09-02): Day 0 support for Meta Muse Spark 1.3 on LiteLLM, with cost tracking for both the standard and contributor tiers.
- [Day 0 support: Gemini 3.8 Flash](https://docs.litellm.ai/blog/gemini_3_8_flash.md) (2026-09-02): day 0 support for Gemini 3.8 Flash on LiteLLM, with launch pricing tracked across Google AI Studio and Vertex AI.
- [Introducing AutoRouter Heuristic v2: 27% More Tasks Solved at 45% Lower Cost](https://docs.litellm.ai/blog/heuristic-v2.md) (2026-09-02): Heuristic v2 is a new classifier for LiteLLM's AutoRouter, pretrained across multiple rounds of graded response data so it ships with zero cold start. On a...
- [Introducing LiteLLM Fusion: 56% More Tasks Solved Than Fable 5](https://docs.litellm.ai/blog/fusion-terminal-bench-benchmark.md) (2026-09-01): LiteLLM Auto Router Fusion ran three models on the same task and synthesized their work, solving 14 of 21 Terminal-Bench tasks against 9 for Claude Fable-5...
- [Auto-Router: Route on Context Size and Modality](https://docs.litellm.ai/blog/auto-router-more-routing-configurations.md) (2026-09-01): The Auto-Router now supports more routing configurations: context-window escalation moves oversized prompts to the cheapest tier that fits them before...
- [Day 0 Support: Claude Fable 5.1](https://docs.litellm.ai/blog/claude_fable_5_1.md) (2026-09-01): Day 0 support for Claude Fable 5.1 on the LiteLLM AI Gateway, with the 0.025x cache read price tracked from the first call.
- [August Townhall Updates: Security, Stability, and Product](https://docs.litellm.ai/blog/august-townhall-updates.md) (2026-08-27): A recap of the August LiteLLM town hall: 79 security fixes, 375 bug fixes, 142 feature commits, a new Director of Security, the public status dashboard, and...
- [Shadow Evaluations: Test the Auto-Router on Your Own Production Traffic](https://docs.litellm.ai/blog/auto-router-shadow-evaluations.md) (2026-08-18): Shadow evaluations duplicate a sampled slice of one key's live traffic through an auto-router and have an LLM judge blindly compare the answers. On our own...
- [Day 0 support: Gemini 3.7 Flash](https://docs.litellm.ai/blog/gemini_3_7_flash.md) (2026-08-13): day 0 support for Gemini 3.7 Flash on LiteLLM, with launch pricing tracked across Google AI Studio and Vertex AI.
- [August Townhall: Product + Roadmap Updates](https://docs.litellm.ai/blog/august-townhall-announcement.md) (2026-08-10): Join the LiteLLM August townhall on Thursday, 27 August at 7:30 AM PT to learn about LiteLLM's product updates and roadmap.
- [51% Cost Savings Reported From a Live Production Deployment](https://docs.litellm.ai/blog/auto-router-production-savings.md) (2026-08-10): A LiteLLM customer rolled the Auto Router out to 450+ users in production and shared four months of numbers: 272,876 requests, 7.08 billion tokens, and...
- [Auto Router: Opus level quality at up to 27% lower cost](https://docs.litellm.ai/blog/auto-router-terminal-bench-benchmark.md) (2026-08-08): On a 21 task subset of Terminal-Bench 2.0, an auto router matched Claude Opus-5 solve rate at 27% lower cost. Adding the last 3 user messages as classifier...
- [AutoRouter: Easy Visibility to Your Savings](https://docs.litellm.ai/blog/auto-router-spend-visibility.md) (2026-08-06): A new Auto-Router Usage tab in Cost Optimization, per-request classifier cost reporting, preset matching against your own deployments, and two routing fixes.
- [AutoRouter: 1 Click Deploy](https://docs.litellm.ai/blog/auto-router-setup-and-testing.md) (2026-08-05): Six changes to the Auto-Router: 1-click Anthropic and OpenAI presets, a one-line agent setup skill, Test Routing in the UI, a replaceable classifier prompt,...
- [Auto Router v1.97: usage benchmarks and better quality for lower cost](https://docs.litellm.ai/blog/auto-router-context-and-benchmarks.md) (2026-08-04): v1.97 adds cost and usage benchmarks for the auto router, gives the LLM classifier a window of prior turns, and turns session affinity off by default. Across...
- [Prompt Caching Works with Auto Router](https://docs.litellm.ai/blog/auto-router-prompt-caching-benchmark.md) (2026-07-31): The most common objection to auto-routing is that switching models throws away your prompt cache. We measured it across five datasets, including real gateway...
- [Cut 75% Claude Code cost with near frontier model quality](https://docs.litellm.ai/blog/auto-router-cost-quality-benchmark.md) (2026-07-27): Two independent evaluations of a four-tier Auto Router config against an all-frontier baseline: 8,619 graded prompts, 14,000 simulated real conversations, and...
- [July Townhall Updates: 38 Security Fixes, 317 Bug Fixes, and Autorouter V2](https://docs.litellm.ai/blog/july-townhall-updates.md) (2026-07-24): A recap of the July LiteLLM town hall: 38 security fixes, 317 bug fixes, 140 feature commits, new Rust gateway benchmarks, and the launch of Autorouter V2.
- [Day 0 Support: Claude Opus 5](https://docs.litellm.ai/blog/claude_opus_5.md) (2026-07-24): Day 0 support for Claude Opus 5 on the LiteLLM AI Gateway. Use it across Anthropic, Azure, Vertex AI, and Bedrock.
- [Benchmarking the LiteLLM Rust AI Gateway: Overhead, Memory, and Cost](https://docs.litellm.ai/blog/rust-ai-gateway-benchmarks.md) (2026-07-22): AIGatewayBench measures the overhead an AI gateway adds on top of the upstream model, isolated against a deterministic mock, across LiteLLM (Rust), LiteLLM...
- [Announcing Router Plugins: Customize Routing Signals](https://docs.litellm.ai/blog/router-plugins-on-the-proxy.md) (2026-07-17): Router plugins are now live on LiteLLM. Configure a plugin pipeline to determine which models to pick for a given input. Plugins can be chained as well
- [Auto Router v2: one router for complexity, semantic, and adaptive routing](https://docs.litellm.ai/blog/autorouter-v2.md) (2026-07-13): Auto Router v2 folds LiteLLM's complexity, semantic, and adaptive routers into a single router with an LLM classifier, keyword tiers, multi-model pools, and...
- [Incident Report: Prompt Cache Invalidation for Claude Code on Bedrock Invoke](https://docs.litellm.ai/blog/bedrock-invoke-prompt-caching-incident.md) (2026-07-13): Date: July 4 to July 10, 2026
- [July stability update: hardening MCP auth and cutting pass-through memory](https://docs.litellm.ai/blog/two-week-stability-update.md) (2026-07-11): A two-week product quality update. We addressed two major issues (MCP credential resolution and pass-through memory) and shipped 134 bug fixes in total. Plus...
- [July Townhall: Product + Roadmap Updates](https://docs.litellm.ai/blog/july-townhall-announcement.md) (2026-07-09): Join the LiteLLM July townhall on Thursday, 23 July at 7:30 AM PT to learn about LiteLLM's product updates and roadmap.
- [Day 0 Support: GPT-5.6 (Sol, Terra, Luna)](https://docs.litellm.ai/blog/gpt_5_6.md) (2026-07-09): Day 0 support for the GPT-5.6 family (Sol, Terra, and Luna) on LiteLLM.
- [5 ways to cut Claude Code costs with LiteLLM](https://docs.litellm.ai/blog/save-claude-code-costs-with-litellm.md) (2026-07-04): Practical levers a platform admin can pull on the LiteLLM proxy to reduce Claude Code spend without asking developers to change a thing.
- [Day 0 Support: Claude Sonnet 5](https://docs.litellm.ai/blog/claude_sonnet_5.md) (2026-06-30): Day 0 support for Claude Sonnet 5 on the LiteLLM AI Gateway. Use it across Anthropic, Azure, Vertex AI, and Bedrock.
- [LiteLLM × Headroom: Use 60-95% fewer tokens with Claude Code](https://docs.litellm.ai/blog/headroom-integration.md) (2026-06-30): Cut input tokens on Claude Code and other LLM traffic by attaching Headroom as a pre_call guardrail on LiteLLM.
- [June Townhall Updates: 94 Bug Fixes, OCR + Realtime are in Rust, and a Zero-Regression Commitment](https://docs.litellm.ai/blog/june-townhall-updates.md) (2026-06-26): A recap of the June LiteLLM town hall covering security hardening, our zero-regression commitment, 78 feature commits, and the gradual migration of the...
- [Swap OpenAI Code Interpreter for E2B/OpenSandbox](https://docs.litellm.ai/blog/swap_openai_code_interpreter.md) (2026-06-23): Keep the OpenAI code_interpreter tool in your requests, run the code in your own sandbox. LiteLLM intercepts the tool call and routes it to E2B or...
- [Migrating LiteLLM to Rust - Building the Fastest and Litest AI Gateway](https://docs.litellm.ai/blog/litellm-rust-launch.md) (2026-06-22): LiteLLM is moving its AI gateway to Rust: 15x throughput, 11x less memory, and sub-1ms per-request overhead. No v2, no migration, your config stays the same.
- [LiteLLM version support: focusing on the four most recent stable lines](https://docs.litellm.ai/blog/version-support.md) (2026-06-20): Starting Monday, June 29, 2026, LiteLLM actively supports the four most recent stable minor lines. Older lines reach end of life, and the window rolls forward...
- [Semantic Caching on Valkey and AWS ElastiCache](https://docs.litellm.ai/blog/valkey_semantic_caching.md) (2026-06-17): LiteLLM now supports semantic prompt caching on Valkey clusters running the valkey-search module, including AWS ElastiCache for Valkey, with no RediSearch,...
- [June Townhall: Product + Roadmap Updates](https://docs.litellm.ai/blog/june-townhall-announcement.md) (2026-06-16): Join the LiteLLM June townhall on Thursday, 25 June at 7:30 AM PST to learn about LiteLLM's product updates and roadmap.
- [June Stability Update: We're Making Stability a First-Class Citizen at LiteLLM](https://docs.litellm.ai/blog/stability.md) (2026-06-15)
- [Day 0 Support: Claude Fable 5](https://docs.litellm.ai/blog/claude_fable_5.md) (2026-06-10): Day 0 support for Claude Fable 5 on the LiteLLM AI Gateway. Use it across Anthropic, Azure, Vertex AI, and Bedrock.
- [A Unified Agent Control Plane](https://docs.litellm.ai/blog/agents-are-the-new-llms.md) (2026-06-10): The AI Gateway is moving up the stack: from routing model calls to routing agent work.
- [Announcing LiteLLM x Microsoft ASSERT](https://docs.litellm.ai/blog/litellm-microsoft-assert.md) (2026-06-03): LiteLLM now integrates with Microsoft ASSERT for policy-driven agent evaluation — catch safety and quality defects before they reach production.
- [LiteLLM Labs: Announcing Lite-Harness SDK — Unified API for Claude Code, Codex, and Pi AI](https://docs.litellm.ai/blog/lite-harness-sdk.md) (2026-06-02): One SDK. Swap between Claude Code, Codex, and Pi AI by changing a string. Pairs with the LiteLLM AI Gateway for keys, budgets, logs, and fallbacks.
- [Fixed in 1.84.0+ - Version Update: Authentication Bypass via Host Header Injection (GHSA-4xpc-pv4p-pm3w)](https://docs.litellm.ai/blog/host-header-auth-bypass.md) (2026-06-01): Disclosure of a Host-header authentication bypass in the LiteLLM proxy. Addressed in v1.84.0. Very limited deployments are potentially affected, and no...
- [Day 0 Support: Claude Opus 4.8](https://docs.litellm.ai/blog/claude_opus_4_8.md) (2026-05-28): Day 0 support for Claude Opus 4.8 on the LiteLLM AI Gateway. Use it across Anthropic, Azure, Vertex AI, and Bedrock.
- [How we built a background agent to cover 30% of our backlog](https://docs.litellm.ai/blog/lap-internal-agent-30-percent.md) (2026-05-27): How we built a background agent on the LiteLLM AI Gateway that merges PRs with no human in the loop (the infra, harness, and credential-scoping calls behind...
- [May Townhall Updates: Security Hardening, Release Versioning, and the Agent Platform](https://docs.litellm.ai/blog/may-townhall-updates.md) (2026-05-26): A recap of the May LiteLLM town hall covering 89 security fixes, new release versioning, MCP toolsets, performance wins, and the LiteLLM Agent Platform.
- [DAY 0 Support: Gemini 3.5 Flash on LiteLLM](https://docs.litellm.ai/blog/gemini_3_5_flash.md) (2026-05-19): Guide to using Gemini 3.5 Flash on LiteLLM Proxy and SDK with day 0 support.
- [Google AI Studio Managed Agents on LiteLLM](https://docs.litellm.ai/blog/google-ai-studio-managed-agents.md) (2026-05-19): LiteLLM now supports the Google AI Studio Managed Agents API. Create, manage, and run custom agents through LiteLLM.
- [May Townhall: Product + Roadmap Updates](https://docs.litellm.ai/blog/may-townhall-announcement.md) (2026-05-19): Join the LiteLLM May townhall on Tuesday, 19 May at 7:30 AM PST to learn about LiteLLM's product updates and roadmap.
- [Announcing Componentized Deployments](https://docs.litellm.ai/blog/componentized-deployment.md) (2026-05-18): How LiteLLM's componentized deployment isolates the management/UI control plane from the LLM data plane, improving reliability at scale.
- [Security Update: Mistral AI PyPI Supply Chain Attack — LiteLLM Not Impacted](https://docs.litellm.ai/blog/mistral-supply-chain-attack-may-2026.md) (2026-05-12): On May 11, 2026, a malicious version of the mistralai PyPI package was published as part of a coordinated supply chain attack. LiteLLM is not affected — we...
- [LiteLLM Managed Agents Platform — Alpha Now Open for Public Preview](https://docs.litellm.ai/blog/agent-platform-alpha.md) (2026-05-08): Spawn sandboxed agent sessions on the LiteLLM Gateway — a control plane for managed agents, now in public preview.
- [Security Update: CVE-2026-42208 in LiteLLM Proxy](https://docs.litellm.ai/blog/cve-2026-42208-litellm-proxy-sql-injection.md) (2026-04-29): CVE-2026-42208 (SQL injection in LiteLLM Proxy's API key verification path) is fixed. Upgrade to v1.83.10-stable.
- [Incident Report: Prisma DB Reconnect Blocks the Event Loop and Kills Liveliness](https://docs.litellm.ai/blog/prisma-reconnect-blocking-incident.md) (2026-04-29): Date: April 2026
- [LiteLLM release versioning is changing: standard names, MINOR for weekly, PATCH for hotfixes](https://docs.litellm.ai/blog/cleaner-release-versions.md) (2026-04-28): Dropping `-stable` and `-nightly` suffixes. Weekly releases bump MINOR; PATCH is now reserved for actual hotfixes. Old releases keep their tags forever; new...
- [Gemini Embedding 2 (GA): Multimodal Embeddings on LiteLLM](https://docs.litellm.ai/blog/gemini_embedding_2_ga.md) (2026-04-24): Use generally available gemini-embedding-2 for multimodal embeddings on LiteLLM via Gemini API and Vertex AI—the same flows as preview, stable model id.
- [Day 0 Support: GPT-5.5 and GPT-5.5 Pro](https://docs.litellm.ai/blog/gpt_5_5.md) (2026-04-24): Day 0 support for GPT-5.5 and GPT-5.5 Pro on LiteLLM.
- [Security Update: CVE-2026-30623 — Command Injection via Anthropic's MCP SDK](https://docs.litellm.ai/blog/mcp-stdio-command-injection-april-2026.md) (2026-04-21): CVE-2026-30623 (authenticated RCE via MCP stdio transport) is fixed. Upgrade to v1.83.6-nightly or v1.83.7-stable or later.
- [LiteLLM × Akto: Model-Based Detection Alongside Built-in Guardrails](https://docs.litellm.ai/blog/akto-partnership.md) (2026-04-21): Chain Akto's model-based detection with LiteLLM's built-in guardrails — catch PII, prompt injection, and policy violations that pattern-based checks miss.
- [Day 0 Support: Claude Opus 4.7](https://docs.litellm.ai/blog/claude_opus_4_7.md) (2026-04-16): Day 0 support for Claude Opus 4.7 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock.
- [Making the AI Gateway Resilient to Redis Failures](https://docs.litellm.ai/blog/redis-circuit-breaker.md) (2026-04-11): How LiteLLM's production AI Gateway handles Redis degradation at scale without cascading failures — circuit breaker pattern, 0ms fast-fail, automatic recovery.
- [April Townhall Updates: CI/CD v2, Stability, and Product Roadmap](https://docs.litellm.ai/blog/april-townhall-updates.md) (2026-04-10): A recap of the April LiteLLM town hall covering CI/CD v2, product stability work, and the near-term roadmap.
- [Security Update: Vulnerability Disclosures and Ongoing Hardening](https://docs.litellm.ai/blog/security-hardening-april-2026.md) (2026-04-03): Disclosure of security vulnerabilities fixed in LiteLLM v1.83.0, and the launch of our bug bounty program.
- [April Townhall: Security + Product Roadmap](https://docs.litellm.ai/blog/april-townhall-announcement.md) (2026-04-02): Join the LiteLLM April townhall on Friday, 10 April at 7:30 AM to learn about LiteLLM's security and product roadmap.
- [Announcing CI/CD v2 for LiteLLM](https://docs.litellm.ai/blog/ci-cd-v2-improvements.md) (2026-03-30): CI/CD v2 introduces isolated environments, stronger security gates, and safer release separation for LiteLLM.
- [LiteLLM + Vanta: SOC 2 Type 2 and ISO 27001 Recertification](https://docs.litellm.ai/blog/vanta-compliance-recertification.md) (2026-03-30): LiteLLM is partnering with Vanta on SOC 2 Type 2 and ISO 27001 recertification and engaging independent auditors for verification.
- [Security Townhall Updates](https://docs.litellm.ai/blog/security-townhall-updates.md) (2026-03-27): What happened, what we've done, and what comes next for LiteLLM's release and security processes.
- [Security Update: Suspected Supply Chain Incident](https://docs.litellm.ai/blog/security-update-march-2026.md) (2026-03-24): As of 2:00 PM ET on March 24, 2026
- [Incident Report: Guardrail logging exposed secret headers in spend logs and traces](https://docs.litellm.ai/blog/guardrail-logging-secret-exposure-incident.md) (2026-03-18): Date: March 18, 2026
- [Day 0 Support: GPT-5.4-mini and GPT-5.4-nano](https://docs.litellm.ai/blog/gpt_5_4_mini_nano.md) (2026-03-17): GPT-5.4-mini and GPT-5.4-nano model support in LiteLLM
- [New Video Characters, Edit and Extension API support](https://docs.litellm.ai/blog/video_characters_api.md) (2026-03-16): LiteLLM now supports creating, retrieving, and managing reusable video characters across multiple video generations.
- [Realtime WebRTC HTTP Endpoints](https://docs.litellm.ai/blog/realtime_webrtc_http_endpoints.md) (2026-03-12): Use the LiteLLM proxy to route OpenAI-style WebRTC realtime via HTTP: client_secrets and SDP exchange.
- [Day 0 Support: GPT-5.4](https://docs.litellm.ai/blog/gpt_5_4.md) (2026-03-05): GPT-5.4 model support in LiteLLM
- [DAY 0 Support: Gemini 3.1 Flash Lite Preview on LiteLLM](https://docs.litellm.ai/blog/gemini_3_1_flash_lite_preview.md) (2026-03-03): Guide to using Gemini 3.1 Flash Lite Preview on LiteLLM Proxy and SDK with day 0 support.
- [Incident Report: Cache Eviction Closes In-Use httpx Clients](https://docs.litellm.ai/blog/httpx-cache-eviction-incident.md) (2026-02-27): Date: February 27, 2026
- [Day 0 Support: GPT-5.3-Codex](https://docs.litellm.ai/blog/gpt_5_3_codex.md) (2026-02-24): Day 0 support for GPT-5.3-Codex on LiteLLM, including phase parameter handling for Responses API.
- [Incident Report: Encrypted Content Failures in Multi-Region Responses API Load Balancing](https://docs.litellm.ai/blog/responses-api-encrypted-content-incident.md) (2026-02-24): Date: Feb 24, 2026
- [Incident Report: Wildcard Blocking New Models After Cost Map Reload](https://docs.litellm.ai/blog/anthropic-wildcard-model-access-incident.md) (2026-02-23): Date: Feb 23, 2026
- [Incident Report: SERVER_ROOT_PATH regression broke UI routing](https://docs.litellm.ai/blog/server-root-path-incident.md) (2026-02-21): Date: January 22, 2026
- [DAY 0 Support: Gemini 3.1 Pro on LiteLLM](https://docs.litellm.ai/blog/gemini_3_1_pro.md) (2026-02-19): Guide to using Gemini 3.1 Pro on LiteLLM Proxy and SDK with day 0 support.
- [Incident Report: vLLM Embeddings Broken by encoding_format Parameter](https://docs.litellm.ai/blog/vllm-embeddings-incident.md) (2026-02-18): Date: Feb 16, 2026
- [Day 0 Support: Claude Sonnet 4.6](https://docs.litellm.ai/blog/claude_sonnet_4_6.md) (2026-02-17): Day 0 support for Claude Sonnet 4.6 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock.
- [Incident Report: Invalid beta headers with Claude Code](https://docs.litellm.ai/blog/claude-code-beta-headers-incident.md) (2026-02-16): Date: February 13, 2026
- [Day 0 Support: MiniMax-M2.5](https://docs.litellm.ai/blog/minimax_m2_5.md) (2026-02-12): Day 0 support for MiniMax-M2.5 on LiteLLM
- [Incident Report: Invalid model cost map on main](https://docs.litellm.ai/blog/model-cost-map-incident.md) (2026-02-10): Date: January 27, 2026
- [Your Middleware Could Be a Bottleneck](https://docs.litellm.ai/blog/fastapi-middleware-performance.md) (2026-02-07): How we improved LiteLLM proxy latency and throughput by replacing a single middleware base class
- [Improve release stability with 24 hour load tests](https://docs.litellm.ai/blog/litellm-observatory.md) (2026-02-06): How we built a long-running, release-validation system to catch regressions before they reach users.
- [Day 0 Support: Claude Opus 4.6](https://docs.litellm.ai/blog/claude_opus_4_6.md) (2026-02-05): Day 0 support for Claude Opus 4.6 on LiteLLM AI Gateway - use across Anthropic, Azure, Vertex AI, and Bedrock.
- [Achieving Sub-Millisecond Proxy Overhead](https://docs.litellm.ai/blog/sub-millisecond-proxy-overhead.md) (2026-02-02): Our Q1 performance target and architectural direction for achieving sub-millisecond proxy overhead on modest hardware.
- [DAY 0 Support: Gemini 3 Flash on LiteLLM](https://docs.litellm.ai/blog/gemini_3_flash.md) (2025-12-17): Guide to using Gemini 3 Flash on LiteLLM Proxy and SDK with day 0 support.
- [Day 0 Support: Claude 4.5 Opus (+Advanced Features)](https://docs.litellm.ai/blog/anthropic_advanced_features.md) (2025-11-25): Guide to Claude Opus 4.5 and advanced features in LiteLLM: Tool Search, Programmatic Tool Calling, and Effort Parameter.
- [DAY 0 Support: Gemini 3 on LiteLLM](https://docs.litellm.ai/blog/gemini_3.md) (2025-11-19): Common questions and best practices for using gemini-3-pro-preview with LiteLLM Proxy and SDK.
- [Gemini Embedding 2 Preview: Multimodal Embeddings on LiteLLM](https://docs.litellm.ai/blog/gemini_embedding_2_multimodal.md) (2025-03-11): Generate embeddings from text, images, audio, video, and PDFs with gemini-embedding-2-preview on LiteLLM via Gemini API (one vector per input,...