Skip to main content
LiteLLM is moving to Rust Read the latest updates.

Changelog

The main changes in each LiteLLM release. Open a release for its full notes, upgrade steps and every merged PR. Watch BerriAI/litellm on GitHub to hear about new releases.

LiteLLM v1.108.12 (LTS) fixes GPT-6.2 caching and Foundry model routers

  • GPT-6.2 caches system prompts on /v1/chat/completions and /v1/messages requests that set store: false, so repeated prompts cost less.
  • azure_ai/model_router entries on a Foundry /openai/v1 base work on /v1/responses and /v1/responses/compact and record the routed model's cost.
  • The tool_policy guardrail applies to tool names longer than 64 characters on /v1/messages, and Vertex batch files with one json_schema row answer every row.
Read the release notes →

LiteLLM v1.110.1, v1.111.0rc2 and v1.106.11 fix GPT-6.2 prompt caching

  • GPT-6.2 caches system prompts on /v1/chat/completions and /v1/messages requests that set store: false, so repeated prompts cost less.
  • Stored requests and previous_response_id follow-ups keep the system prompt in instructions, so follow-up turns do not send the prompt twice.
  • On v1.110.1 the UI image runs on slim nginx without curl, so change exec probes on that image to wget.
Read the release notes →

LiteLLM v1.111.0rc1 adds Customer Management and performance alerts

  • Customer Management adds customer organizations, teams and members, each with its own budgets, rate limits and daily usage in the dashboard.
  • Performance alerts flag spend and traffic spikes, slower responses and higher error rates against the previous seven days, and are on by default.
  • Claude Fable 5.2 and Mythos 5.2, Gemini 4 Carbon and Hydrogen, and 1,020 new fal.ai and Replicate models join the model catalog.
  • The Docker image now runs as non-root, helm/litellm is the only chart, and LITELLM_EMAIL_FALLBACK_LINKS_ANY_USER=true restores the old SSO email matching.
Read the release notes →

LiteLLM v1.110.0 adds the Agent Skills Hub and a Rust-only router

  • The router always runs on the Rust core, and a router config that the Rust core declines now stops the proxy at startup.
  • Spend goes through the LiteLLM_SpendLogDelivery ledger by default, and general_settings.use_spend_logs_ledger: false restores the previous spend queues.
  • The Agent Skills Hub adds skill upload and import, version history and an admin review queue for member submissions.
  • Model and pass-through routes refuse Azure login fields such as client_id and tenant_id in the request body, so move them into metadata.
Read the release notes →

LiteLLM v1.108.7 (LTS) adds Gemini batches and Bedrock image search

  • /v1/batches runs Gemini batches with output download through /v1/files, and Bedrock knowledge bases accept image search with query_image.
  • Azure AI Foundry deployments support gpt-image edits, and Gemini image calls bill text, thinking and Vertex Priority tokens at the correct rates.
  • Responses-only fields such as max_tool_calls return 400 on providers bridged through chat completions unless you set drop_params: true.
Read the release notes →

LiteLLM v1.109.0 adds 11 providers, Codex tool search and daily limits

  • LiteLLM adds 11 providers, including ai&, StreamLake, OpenInfer and BigModel, among 311 new model catalog entries.
  • Codex discovers MCP tools through tool search, and deployments accept rpd and tpd daily limits.
  • Streams that stall, abort or end without a finish reason now fail visibly, so retries, cooldowns and fallbacks apply to them.
  • Claude models missing from the cost map now default to max_tokens: 128000, and DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS=4096 keeps the old value.
Read the release notes →

Older releases are listed in the sidebar.