NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
PyPI, #295 most downloaded on PyPI
Library to easily interface with LLM API providers
Latest stable
1.110.2
Last release today
21 Nov 2026
Ships on a steady schedule
a new release about every 8 days
Nearly every release is documented
notes for 60 of the last 60 stable releases
4 versions withdrawn
withdrawn after publishing
3 years old
1340 releases · first in 2023
Drag across the ruler to compare, or tap a release to open it.
feat(proxy): log keys and teams still on the deprecated empty models defaults at boot by @paveln83 in #50720
cosign verify \
--certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \
--certificate-oidc-issuer https://token.actions.githubusercontent.com \
ghcr.io/berriai/litellm:v1.111.0-rc.1Note truncated.
Your coding agent can read these notes before it upgrades. Set up the MCP server →
Fixed shutdown dates on Gemini TTS and Live preview models to match Google's deprecations page
Important
Signing has moved to keyless cosign. Since v1.111.0-dev.3, releases are signed with Sigstore keyless signing (GitHub OIDC) instead of the cosign.pub key.
cosign verify --key ... does not work for this release. Use the command below. Earlier releases still verify with the key.
cosign verify \
--certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \
--certificate-oidc-issuer https://token.actions.githubusercontent.com \
ghcr.io/berriai/litellm:v1.111.0-dev.4Same command for docker.io/litellm/litellm and the Helm chart at ghcr.io/berriai/litellm/chart/litellm:1.111.0-dev.4
138 PRs. 18 added, 69 fixed, 11 changed, 3 improved, 1 removed. 2 need action
general_settings.redact_tokens_in_spend_logs: true to keep token scanning in spend logs (#51729)service_tier values from Bedrock requests (#50516)filters support and hybrid keyword plus vector search (#51131)budget_limits windows on internal users (#51763)RecursionError on every completion call when litellm.model_fallbacks is set (#51817)azure/ Responses and chat calls to Foundry project /openai/v1 bases (#51767)gpt-image-2.6-sunburst and gpt-image-2.6-flare, billed at twice the rate before (#51647)openai/responses/ chat completions (#51802)azure_ai/claude-haiku-4-5 and azure_ai/claude-opus-4-5 to 2027-03-16 (#51716)reasoning_effort 400 and dropped reasoning_content for Kimi K3 on azure_ai (#51747)azure/ Responses and chat calls to Foundry project /openai/v1 bases (#51767)/v1/messages for Claude on Azure AI Foundry to run on the Rust gateway (#51721)s3:// image, document or video URLs (#50577)/v1/messages streams still reading from Bedrock (#50657)filters and ignored drop_params (#51291)/invoke passthrough not being billed or logged (#51701)service_tier values and to forward reserved (#50516)max_tokens for versioned Claude ids on Vertex AI (#40376)gemini-embedding-2 reporting 0 tokens and $0 cost (#51673)document_ocr, audio_track_extraction and auto_truncate being dropped on Gemini embeddings (#51686)delta.audio (#51750)anyOf, oneOf or allOf schema (#51835)github_copilot/gemini-4-hydrogen to the model cost map (#51696)runwayml/seedance2_5, billed at the 720p rate before (#51697)finish_reason: stop (#50210)COHERE_API_BASE (#50249)HUGGINGFACE_API_BASE and crashing with env endpoints and huggingface/tgi (#51449)low and medium reasoning effort being sent as high for mistral/mistral-large-4 (#51693)opencode_go Messages-protocol models through chat completions (#51715)together_ai/* listing retired Together models that answer 400 (#51827)allowed_openai_params is a string or tuple on Responses models, broken since v1.109.0-rc.1 (#51751)/v1/messages calls routed to OpenAI or Azure (#51305)thinking, system and tools params on Messages requests (#51834)filters support and hybrid keyword plus vector search (#51131)thinking, reasoning effort and tool_choice (#51079)tool_choice on the count routes (#51133)/v1/messages/count_tokens to answer 400 instead of 500 for messages missing role or content (#51284)resources/read failing on the aggregate /mcp endpoint with two or more servers (#51462)cache_control being dropped on tool plus reasoning chat requests sent over Responses (#51783)temperature and output-token limits from routed prompts (#51702)/model_group/info missing key aliases and team model aliases (#51754)tpm requests to fail at once with an error naming the request size (#51838)fal_ai Seedream v5 Pro US text-to-image and edit pricing (#51881)register_model(url) calling out in offline mode (#51545)langfuse_span_scope for key and team Langfuse destinations (#51726)langfuse_otel traces with OTel v2 (#51385)/v1/messages missing from logged messages (#51699)litellm_dynamic_limiter_share_tokens gauge for uncapped teams served while the model is idle (#51709)openai/responses/ chat calls (#51787)budget_limits windows on internal users (#51763)401 Expired Key in Claude Code after a lite login --pkce --config-claude key expires, broken since v1.102.0 (#51319)No available models (#51663)budget_override_expires_at being stored on customer rows with no budget_override (#51667)12months or 1month resetting every midnight instead of on the calendar schedule (#51672)/customer/new budgets resetting on a different schedule than other budget endpoints (#51689)ExceededBudget persisting after a customer budget reset (#51694)budget_override (#51703)/queue/chat/completions skipping budget checks and request_tag_mappings (#51753)No cap for monthly and yearly budgets (#51658)litellm-proxy package version, broken since v1.110.0-dev.2 (#51807)/v1/messages streaming callbacks on SDK installs without redis, broken since v1.98.0 (#51685)RecursionError on every completion call when litellm.model_fallbacks is set (#51817)generateContent serving for custom providers (#51083)cancel_on_disconnect not applying to /v1/rerank (#51252)AttributeError on parallel first requests to a fresh worker (#51591)fix(ui): rename Customer Portal to Customer Management
Co-Authored-By: Ishaan Jaffer 155045088+ishaan-berri@users.noreply.github.com
Co-Authored-By: Ishaan Jaffer 155045088+ishaan-berri@users.noreply.github.com
Co-Authored-By: Ishaan Jaffer 155045088+ishaan-berri@users.noreply.github.com
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: Ishaan Jaffer 155045088+ishaan-berri@users.noreply.github.com
Warning
This release was only partly published. Use v1.111.0-dev.4 instead.
It is built from the same commit and fixes the publishing problems below.
Important
Signing has moved to keyless cosign. This is the first release signed with Sigstore keyless signing (GitHub OIDC) instead of the cosign.pub key.
cosign verify --key ... does not work for this release or later ones. Use the command below. Earlier releases still verify with the key.
pip install "litellm[proxy]==1.111.0.dev3" failed at first, because the litellm-proxy-extras and litellm-enterprise versions it pins were not on PyPI yet. They are published now, so the install workslitellm sdist and the litellm-proxy wheels for this versionThe Docker image, Helm chart and PyPI wheels of this release are otherwise the same code as v1.111.0-dev.4. See its notes for what changed
cosign verify \
--certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \
--certificate-oidc-issuer https://token.actions.githubusercontent.com \
ghcr.io/berriai/litellm:v1.111.0-dev.3All LiteLLM Docker images are signed with cosign . This release is signed with the key introduced in commit e82a3c6 .
All LiteLLM Docker images are signed with cosign. This release is signed with the key introduced in commit e82a3c6.
Verify using the pinned commit hash (recommended):
A commit hash is cryptographically immutable, so this is the strongest way to ensure you are using the published signing key:
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.111.0-dev.2Verify using the release tag (convenience):
Tags are protected in this repository and resolve to the same key. This option is easier to read but relies on tag protection rules:
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/v1.111.0-dev.2/cosign.pub \
ghcr.io/berriai/litellm:v1.111.0-dev.2Expected output:
The following checks were performed on each of these signatures:
- The cosign claims were validated
- The signatures were verified against the specified public key
Full Changelog: v1.111.0-dev.1...v1.111.0-dev.2
One column per quarter.