Release Notes
LiteLLM ships new releases regularly with new provider support, performance improvements, and enterprise features. Use the sidebar to browse all releases.
Latest Release​
v1.87.0 — OCI Generative AI Provider, Gemini 3.5 Flash Day-0, MCP UI for OAuth Servers​
May 23, 2026
OCI Generative AI as a first-class provider (chat, embeddings, streaming, reasoning, tool use across Cohere, Llama, Grok, Gemini, and GPT-5 on OCI with full pricing catalog), Gemini 3.5 Flash and Gemini 3.1 Flash-Lite day-0 on Vertex AI / Google AI Studio / OpenRouter, MCP UI for OAuth-protected tool calls plus Cursor MCP OAuth, Codex CLI JWT team-alias and SSO form-URL auth hardening, and a hot-path Anthropic /v1/messages streaming rewrite with byte-identical wire output and ~90% lower TTFT overhead measured on a real 4-pod deployment.
Latest Release Candidate​
v1.88.0rc3 — Claude Opus 4.8, MCP Access-Group Authorization & Typed OpenTelemetry​
June 4, 2026
Claude Opus 4.8 across Anthropic, Bedrock (with global / us / eu / au regional routes), Azure AI, and Vertex at 1M context with adaptive thinking and output_config goal mode, a full rework of MCP access-group authorization (key and team access groups resolve to MCP servers, additive opt-in grants, stateful/stateless session routing), typed semconv-aligned OpenTelemetry spans carrying team_metadata and http.route on inference spans, and a ~30% cheaper per-chunk Anthropic/Bedrock streaming path.
Recent Releases​
| Version | Date | Highlights |
|---|---|---|
| v1.87.0 | May 23, 2026 | OCI Generative AI provider, Gemini 3.5 Flash day-0, MCP UI for OAuth servers |
| v1.86.0 | May 16, 2026 | Weighted-Routing Failover, native Anthropic web-search citations, OTel-standard server spans |
| v1.85.1 | May 20, 2026 | Patch — Gemini 3.5 Flash day-0 + cross-pod spend fix |
| v1.84.1 | May 20, 2026 | Patch — Gemini 3.5 Flash day-0 + cross-pod spend fix |
| v1.85.0 | May 16, 2026 | Realtime GA, MCP Gateway expansion & hardened multi-tenancy |
| v1.84.0 | May 14, 2026 | Reliability hardening + multi-pod budget accuracy |
| v1.83.14 | Apr 27, 2026 | GPT-5.5, Prompt Compression & Memory API |
| v1.83.10 | Apr 27, 2026 | Claude Opus 4.7, Prompt Compression & Multi-Window Budgets |
| v1.82.3 | Mar 16, 2026 | Nebius AI, gpt-5.4, Gemini 3.x, FLUX Kontext, and 116 new models |
| v1.82.0 | Feb 28, 2026 | Realtime Guardrails, Projects Management, and 10+ Performance Optimizations |
| v1.81.14 | Feb 21, 2026 | New Gateway Level Guardrails & Compliance Playground |
| v1.81.12 | Feb 14, 2026 | Guardrail Policy Templates & Action Builder |
| v1.81.9 | Feb 7, 2026 | Control which MCP Servers are exposed on the Internet |
| v1.81.6 | Jan 31, 2026 | Logs v2 with Tool Call Tracing |
| v1.81.3 | Jan 26, 2026 | Performance — 25% CPU Usage Reduction |
| v1.81.0 | Jan 18, 2026 | Claude Code — Web Search Across All Providers |
| v1.80.15 | Jan 10, 2026 | Manus API Support |
| v1.80.8 | Dec 6, 2025 | Introducing A2A Agent Gateway |
| v1.80.5 | Nov 22, 2025 | Gemini 3.0 Support |
| v1.80.0 | Nov 15, 2025 | Introducing Agent Hub: Register, Publish, and Share Agents |
| v1.79.3 | Nov 8, 2025 | Built-in Guardrails on AI Gateway |
| v1.79.0 | Oct 26, 2025 | Search APIs |
| v1.78.5 | Oct 18, 2025 | Native OCR Support |
| v1.78.0 | Oct 11, 2025 | MCP Gateway: Control Tool Access by Team, Key |
| v1.77.7 | Oct 4, 2025 | 2.9x Lower Median Latency |
| v1.77.5 | Sep 29, 2025 | MCP OAuth 2.0 Support |
| v1.77.3 | Sep 21, 2025 | Priority Based Rate Limiting |
Stay Updated​
- GitHub: Watch the BerriAI/litellm repository for release notifications
- Discord: Join our community for announcements
- Twitter: Follow @LiteLLM
Use the sidebar to browse the full release history.