Langfuse 4.81.0
Langfuse released version 4.81.0, adding Google Vertex AI support to the AI Gateway, dataset item filtering by status, Gemini decision models for evaluators, and Postgres audit log backfilling to ClickHouse. Additional updates include topic map snapshots, custom session views, and telemetry normalization.
Also shipped Nov 16, 2026Langfuse in November 2026 →
Deferred tier for asynchronous model calls on the Interactions API
Google Cloud announced general availability for the Deferred tier on the Gemini Enterprise Agent Platform. It offers a 50% discount compared to Standard PayGo rates for asynchronous Gemini model calls, providing a 24-hour completion window and 7-day state retention.
DeepSeek-V4.1-Flash-1017 is available in Public Preview
DeepSeek-V4.1-Flash-1017 is available in public preview as a fully managed model in Vertex AI Model Garden. The updated model features improved reasoning, coding, agentic, and visual capabilities, supporting multimodal inputs with up to 1M context tokens.
OpenAI CSAM Image Classifier is now available at no cost for approved organizations
OpenAI made its CSAM Image Classifier available at no cost to approved organizations. The tool returns separate classification signals for potential child sexual abuse material and potential AI-generated CSAM to assist human review processes.
Budget limit increased to 40,000 budgets per account
GitHub increased the maximum budget limit for GitHub Enterprise Cloud accounts from 10,000 to 40,000 budgets. The limit applies automatically on github.com and GHE.com to support organizations managing spending across many users and cost centers.
Workforce Identity Federation is GA for Looker Google Cloud core instances
Workforce Identity Federation is now generally available as the primary authentication method for Looker (Google Cloud core) instances using public secure, private, or hybrid connections. It can be configured using the Google Cloud console or gcloud CLI during instance creation or updates.
GitHub Copilot models deprecated on November 16, 2026
GitHub deprecated Claude Opus 4.8, Claude Opus 5, and GPT-5.6 Terra across most GitHub Copilot features. Alternative models including Claude Opus 5.5 and GPT-6 variants are automatically enabled for Copilot Enterprise and Business subscriptions under standard settings.
More from LangfuseEvery Langfuse release →
Langfuse 4.82.0
Langfuse 4.82.0 includes updates to API keys, audit logs, and various fixes for SSRF prevention, prompt logging, and experiment performance.
Langfuse 4.83.0
Langfuse released version 4.83.0, adding a Scatter view for topics, item navigation within annotation queues, updated MCP protocol support, and per-key/per-user AI gateway spend budgets.
Langfuse 4.80.0
Langfuse version 4.80.0 adds Google AI Studio and Microsoft Azure as AI gateway providers. The release also includes ClickHouse query parameter updates, topic filtering in tracing tables, and prompt label management via API and MCP.
Langfuse 4.79.0
Langfuse 4.79.0 makes OpenRouter, xAI, and Vercel AI Gateway generally available, records audit logs for MCP tools, and seeds default score configurations.
Langfuse 4.78.0
Langfuse 4.78.0 introduces new features including an external HTTP code eval dispatcher, Bedrock availability in all environments, and enhanced RBAC with user API key scopes. It also adds improvements to the Topics setup flow and experiment list views.
Langfuse 4.77.0
⚠️⚠️⚠️ This release removes automatic tokenization, as we believe no one should be relying on it. Read our change log to learn more. ⚠️⚠️⚠️ Features - feat(topics): proper cost tracking for executions - feat(external-media-storage): make external media storage an enterprise feature - feat(web): use Langfuse by ClickHouse logo in the app shell and auth...
Langfuse 4.76.0
Langfuse 4.76.0 introduces chronological session list views, topic summaries for the public API and MCP, and improved audit logging for read-access events. The release also includes performance optimizations for ingestion and prompt resolution.
Langfuse 4.75.0
Langfuse 4.75.0 increases AI Gateway limits to 10k requests per minute, simplifies Codex setup, and adds analytics for gateway members.