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4 versions withdrawn
withdrawn after publishing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.
cosign verify \ --key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \ ghcr.io/berriai/litellm:
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.109.0-dev.1Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
704 PRs. 113 added, 312 fixed, 46 changed, 11 improved, 8 removed. 15 need action
cosign.pub key (#48103)chunk.choices[0] reads with if chunk.choices: when include_usage is set (#47109)drop_params: true or stop sending temperature, top_p and top_k to Gemini 3.6 Flash, 3.5 Flash-Lite and newer (#47645)max_input_tokens and max_output_tokens instead of max_tokens from the cost map (#48471)max_tokens on requests to unmapped Anthropic models, or set DEFAULT_ANTHROPIC_CHAT_MAX_TOKENS to 4096 (#48502)streaming_buffer_until_moderated: true on the guardrail if converse-stream replies still need masking (#46307)budget_duration and budget_id changes on keys as an admin, since owners and team members now get 403 (#47681)personal_key_model_access_from_teams is on, grant needed MCP servers and agents to owners' teams first (#46293)tag_routing_prefix to caller routing tags, or move them to the key or team (#47428)litellm.Timeout and request_timeout where you matched 500 APIConnectionError or server_error (#47198)image_tag or all four *_image URIs when sourcing the Terraform module from a git ref (#46960)tpm on Gemini TTS deployments, since limits now count TTS tokens (#44551)guardrailConfig on every Bedrock call (#48278)completion() and responses() failing with No module named 'mcp' on base SDK installs, broken since v1.106.0 (#45961)openinfer/<model> calls and spend tracking (#41034)LITELLM_OFFLINE_MODE to turn off every fetch LiteLLM makes on its own with one switch (#48096)model_info.pricing_provider to price a deployment from another provider's catalog rates instead of $0 (#47620)mp3, opus, alaw and mulaw output (#31915)agent_access_default_deny to stop keys with no agent grants from reaching every agent (#43979)gpt-6.1-terra with pricing (#48429)prompt_cache_retention such as 24h being silently dropped instead of sent upstream (#47480)openai/gpt-5.6 and newer billing at the 30-minute rate (#48088)/v1/responses 404 on dated api_version deployments and azure_ai Grok reasoning token billing (#46377)client_secrets and an invalid token on the SDP exchange (#47316)[System: ...] message being added to tool-call-only assistant turns sent to Anthropic (#34822)json_schema answers losing keys listed only in required and escaping non-ASCII characters, broken since v1.107.0-rc.1 (#47478)redacted_thinking blocks being dropped, and Bedrock Converse 400s when sent twice (#47489)dictionary changed size during iteration errors during price reloads (#41523)invalid beta flag on Claude Code auto mode requests that carry no safeguards (#44471)/v1/realtime tool calls arriving with empty arguments and sessions breaking on flat tools (#46214)post_call guardrails not scanning Claude output on invoke-with-response-stream passthrough (#46524)json_schema streams dropping reasoning and thinking blocks and ending on tool_calls with no tool calls (#46863)json_schema requests by trying native output first (#47100)/bedrock pass-through routes to apply a model's guardrailConfig, returning 400 if Bedrock cannot use it (#47429)cachedContents on every call and creating duplicate caches (#46857)text-embedding-005 and text-multilingual-embedding-002 billing per token instead of per character (#47460)/v1/messages (#48523)/v1/videos, with prices for the four models (#46156)/v1/search provider with search_provider: deepseek (#47401)/v1/extraction endpoint with Cloudflare Clairic support (#47473)reasoning_effort being dropped (#48498)Note truncated.
Your coding agent can read these notes before it upgrades. Set up the MCP server →
cosign verify \ --certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \ --certificate-oidc-
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:v1.108.15Full Changelog: v1.108.14...v1.108.15
Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
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:v1.108.14Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
3 PRs. 1 added, 1 fixed. No action needed to upgrade
/v1/responses follow-up turns, which led to 400s from Anthropic (#50821)input_json content parts on /v1/decisions (#52807)Backport #53007 · Full changelog
Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
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:v1.108.13Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
7 PRs. 5 fixed. No action needed to upgrade
/v1/chat/completions and /v1/messages unless store: false (#52906) Also in 1.106.12, 1.109.3, 1.110.2jwt_issuer taking 5 minutes to apply when litellm_jwtauth.issuers is set, broken since v1.103.0 (#52350) Also in 1.109.3, 1.110.2/key/info letting a key with no user read other userless keys by hash or alias (#52838, #52925) Also in 1.106.12, 1.109.3, 1.110.2localhost:5432 (#52797)Backport #52713 · Backport #52819 · Backport #52907 · Backport #52919 · Full changelog
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:v1.108.13Full Changelog: v1.108.12...v1.108.13
Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
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:v1.108.12Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
8 PRs. 6 fixed. No action needed to upgrade
/v1/chat/completions or /v1/messages with store: false (#52621, #52739)azure_ai/model_router on a Foundry /openai/v1 base failing on /v1/responses and /v1/responses/compact (#52474)json_schema row failing every other row in a Vertex batch file (#51790)Tool reference '<name>' not found on /v1/messages when a guardrail sees a tool name over 64 characters (#47434)/v1/messages that keep streaming upstream after the caller closes the stream (#52144)tool_policy letting /v1/messages requests through when a blocked tool name is over 64 characters (#52717)Backport #52476 · Backport #52666 · Backport #52725 · Full changelog
cosign verify \ --certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \ --certificate-oidc-
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:v1.108.11Full Changelog: v1.108.10...v1.108.11
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
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:v1.108.11Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
22 PRs. 1 added, 14 fixed, 2 changed. No action needed to upgrade
reasoning_effort to DeepSeek V4 Flash and Pro on azure_ai (#52070)guarded_text parts in system and assistant messages being dropped instead of checked by the guardrail (#51776)/v1/messages that kept generating billed output tokens upstream (#52210)reasoning_effort: "xhigh" to gemini-4-hydrogen (#52060)COHERE_API_BASE and always calling api.cohere.ai (#52194)finish_reason: stop that broke strict clients (#52200)fake_stream params reaching provider request bodies and causing 400s (#52225)/v1/responses when allowed_openai_params is a string or tuple (#52203)signature_delta, so clients dropped them on the next tool step (#52117)n, size, quality and the other OpenAI image params (#52051)os.environ/ values, team admins now get 403 (#51874)/sso/key/generate/ and redirecting to http:// behind TLS termination, broken since v1.108.0 (#52213)curl but keeps wget and nc (#52298)LITELLM_RUST=true (#51812)generateContent support for custom providers registered in custom_provider_map (#51083)Backport #51982 · Backport #52074 · Backport #52155 · Backport #52201 · Backport #52233 · Backport #52248 · Backport #52306 · Backport #52312 · Full changelog
cosign verify \ --certificate-identity https://github.com/BerriAI/project-releaser/.github/workflows/release.yml@refs/heads/main \ --certificate-oidc-
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:v1.108.10Full Changelog: v1.108.9...v1.108.10
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
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:v1.108.10Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
8 PRs. 3 fixed. No action needed to upgrade
claude-*@<version> models stopping at 4096 tokens when max_tokens is unset (#51863)file part and streamed PDF URLs stalling the proxy worker (#51860)base_model is azure/eu/o3, o4-mini, o1 or o3-mini (#47497)Backport #51412 · Backport #51875 · Full changelog
All 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:v1.108.9Verify 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/v1.108.9/cosign.pub \
ghcr.io/berriai/litellm:v1.108.9Expected 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: v1.108.8...v1.108.9
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.9Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
10 PRs. 2 added, 7 fixed, 1 changed. No action needed to upgrade
reasoning_effort (#51747)/openai/v1 bases and 404 on resource-level /openai/v1 Responses bases (#51767)s3:// image, PDF and video URLs on Converse models, which now go to Bedrock as S3 sources (#50577)vertex_request_label_fields to label Vertex calls with the caller's key, team, org and project (#50732)Extra inputs are not permitted when sending labels to Claude on Vertex AI (#48753)/v1/decisions, billed at the cost Vercel reports (#50642)/v1/responses dropping the first answer fragment when it arrives together with reasoning (#51356)cache_control marks being dropped on chat requests with function tools bridged to the Responses API (#51783)Backport #50401 · Backport #51250 · Backport #51292 · Backport #51748 · Backport #51769 · Backport #51786 · Backport #51796 · Full changelog
All 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:v1.108.8Verify 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/v1.108.8/cosign.pub \
ghcr.io/berriai/litellm:v1.108.8Expected 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: v1.108.7...v1.108.8
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.8Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
4 PRs. 3 fixed. No action needed to upgrade
/v1/decisions for azure/ deployments (#51460)files/<id> or its URL (#51503)Authentication incomplete on servers that answer mcp_all with detailed scopes, broken since v1.107.0 (#51578)Backport #51640 · Full changelog
Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.7Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
14 PRs. 3 added, 8 fixed, 1 changed. 1 needs action
drop_params: true or stop sending Responses-only fields such as max_tool_calls to providers bridged through chat completions (#48655) Also in 1.109.0query_image, including image hits in the results (#51062)/gemini batchGenerateContent batches logging $0 with model unknown instead of billing the calling key (#51279)reasoning_effort being dropped or rejected for Baseten models (#40152) Also in 1.109.0baseten/* listing retired deployment IDs instead of the current Baseten Model APIs (#46945) Also in 1.109.0sequence_number on bridged /v1/responses streaming events (#44944)previous_response_id chain contains a failed turn (#48647) Also in 1.109.0max_tool_calls to answer 400 on bridged providers unless drop_params is on (#48655) Also in 1.109.0/v1/batches, with output download through /v1/files and spend tracking (#51032)Backport #51262 · Backport #51266 · Backport #51271 · Backport #51340 · Full changelog
All 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:v1.108.6Verify 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/v1.108.6/cosign.pub \
ghcr.io/berriai/litellm:v1.108.6Expected 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: v1.108.5...v1.108.6
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.6Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
16 PRs. 7 fixed, 2 changed. 1 needs action
tenant_id, client_id, client_secret, azure_username, azure_password and azure_scope request tags into metadata (#51254) Also in 1.106.9reasoning_effort being bridged to /v1/responses (#50968)/v1/responses calls that send an allowed_tools tool choice (#50726)client_id, client_secret, tenant_id and Azure login fields (#51254) Also in 1.106.9/user/daily/activity/aggregated (#51043)Backport #50435 · Backport #51064 · Backport #51122 · Backport #51229 · Backport #51240 · Backport #51260 · Full changelog
Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.5Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
5 PRs. 4 fixed. No action needed to upgrade
ollama_chat/ streams giving every parallel tool call index 0, so clients ran only the first call (#50718)/v1/messages answering 400 for a param listed in the deployment's additional_drop_params (#50755)Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.4Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
10 PRs. 7 fixed, 1 changed. No action needed to upgrade
/bedrock pass-through routes to enforce the model's guardrailConfig over any guardrail the caller sends (#47429)chatgpt/ models on /v1/messages dropping encrypted reasoning between turns (#50456)/v1/messages to OpenAI sending background: true upstream, which billed full runs that came back empty (#50462)/v1/videos polls failing with per-model keys or hitting the wrong provider account with a 404 (#44614)completion(), responses() and messages with tools failing with No module named 'mcp' on a base install, broken since v1.106.0 (#45961)Backport #50568 · Backport #50605 · Backport #50693 · Full changelog
Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.3Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
11 PRs. 3 fixed. No action needed to upgrade
api_base: "", which answered 500 or 400 (#50449)SSE stream ended without a response, broken since v1.103.0 (#47034)post_call guardrails checking each response twice and calling the moderation provider twice (#50463)Backport #50484 · Backport #50487 · Full changelog
Tip The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
cosign verify \
--key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
ghcr.io/berriai/litellm:v1.108.2Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images
12 PRs. 11 fixed, 1 changed. No action needed to upgrade
openai/ deployments with an empty api_key sending OPENAI_ADMIN_KEY as the bearer token (#50218)service_tier so unsupported tiers answer 400 and reserved, auto and standard_only are honored (#50360)per-turn-control-2026-07-01 beta on Claude 4.5 and newer (#50362)vertex_location, so US and EU deployments call their multi-region host (#50392)response_format: json_object on openai/responses/* and azure/responses/* answering 400 about the word json (#50267)image_url answering 400, and Bedrock JSON schema calls dropping thinking (#50280)/v1/responses/compact returning 500 when a during_call guardrail is on by default (#50274)drop_params (#50348)turn_off_message_logging is on (#50276)Backport #50297 · Backport #50326 · Full changelog
All 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:v1.108.1Verify 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/v1.108.1/cosign.pub \
ghcr.io/berriai/litellm:v1.108.1Expected 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: v1.108.0...v1.108.1
Tip
The lts image tag always points to the latest LTS release. Pull ghcr.io/berriai/litellm:lts to stay on the newest LTS patch
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:v1.108.1Verify 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/v1.108.1/cosign.pub \
ghcr.io/berriai/litellm:v1.108.1Expected 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: v1.108.0...v1.108.1
One column per quarter.