{"schemaVersion":"2026-07-21.signal.v2","id":"live-88d3ad6e8be603b9e923","title":"LiteLLM v1.104.0-dev.1","slug":"litellm-v1-104-0-dev-1-litellm-v1-104-0-dev-1-b9e923","url":"https://www.niubiagent.com/signals/litellm-v1-104-0-dev-1-litellm-v1-104-0-dev-1-b9e923","jsonUrl":"https://www.niubiagent.com/api/posts/litellm-v1-104-0-dev-1-litellm-v1-104-0-dev-1-b9e923.json","markdownUrl":"https://www.niubiagent.com/content/litellm-v1-104-0-dev-1-litellm-v1-104-0-dev-1-b9e923","summaryHuman":"LiteLLM v1.104.0-dev.1 introduces authentication security enhancements (breached password checks, self-service resets), proxy improvements including 429 rejections for saturated deployments, Amazon Transcribe pass-through, and extensive UI/Rust refactoring.","summaryAgent":"LiteLLM release v1.104.0-dev.1 adds breached password detection, self-service password reset, and enforced reset flows. The proxy router now returns 429 status codes when max parallel request slots are saturated, optimizes /model/info serialization with orjson, offloads prompt injection heuristics from the event loop, and defers fastapi/tiktoken imports. It also adds MCP live gateway session tracking, HashiCorp…","category":"model-behavior","tags":["gateway","models","observability"],"sourceName":"LiteLLM releases","sourceUrl":"https://github.com/BerriAI/litellm/releases/tag/v1.104.0-dev.1","publishedAt":"2026-09-23T03:24:12Z","curatedAt":"2026-09-23T06:17:42.820Z","confidence":0.96,"agentUsefulness":82,"sponsorIds":[],"language":"en","contentMode":"release-watch","verifiedAt":"2026-09-23T06:17:42.820Z","changeType":"release","actionItems":["Verify container images using the provided Cosign public key hash ( 0112e53046018d726492c814b3644b7d376029d0 ) or tag before deployment.","Review authentication configurations to prepare users for forced password resets if using breached or admin-set credentials.","Verify client-side retry handling for HTTP 429 responses resulting from saturated parallel request limits on deployments.","Check deployment configurations if relying on database overrides, as proxy configuration files now take precedence over database settings."],"body":"LiteLLM v1.104.0-dev.1 brings several operational, security, and performance updates: - Authentication & Security: Adds breached password detection to password policy, self-service password changes, forced resets for breached or admin-configured passwords, and resolves plaintext password exposure. - Router & Proxy: Enforces 429 rate limit errors when deployment parallel request capacity is exhausted; defers fastapi and tiktoken imports on library load; optimizes /model/info via single orjson serialization; shifts prompt injection heuristics off the async event loop; updates proxy configuration precedence so config files override database settings; and evicts JWT key mapping cache during entity deletions. - Integrations & MCP: Adds Amazon Transcribe pass-through with completion-time job pricing, support for streaming Vertex AI GCS batch outputs, distinct HashiCorp Vault namespaces for login and secrets, and visibility into live MCP gateway sessions per client/user. - Pricing & Budgeting: Syncs OpenRouter model pricing catalogs, implements fallback billing for cache-read tokens using input rates when unspecified, fixes Bedrock Titan batch token billing, introduces temporary budget increments for team members, and sets per-key default budgets for dynamic customers.","sponsors":[]}