BerriAI/litellm v1.104.6 on GitHub

Important

The image-signing key has changed. Starting with this release, every Docker image and Helm chart is signed with the new cosign key from commit e82a3c6. Verifying with the previous key from commit 0112e53 will fail.

Update anything that pins the old cosign.pub: cosign verify scripts, CI checks, and admission policies such as Kyverno, Sigstore policy-controller or Connaisseur.

New cosign.pub SHA-256: e3fe3e08c44b16407fe0b37c43b4f8b603b3a0f4ee74c29e647bc022d762c2c0

Verify this release

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/e82a3c646908ba0a6ee0beddc4310d7a6cac4065/cosign.pub \
  ghcr.io/berriai/litellm:v1.104.6

Same command for litellm-database, litellm-non_root and the docker.io/litellm/* images

What's new in 1.104.6

17 PRs. 11 fixed, 2 changed, 1 removed. 1 needs action

Action required

Deployment: Verify image signatures with the cosign.pub from commit e82a3c6, the previous key no longer matches (#48103) ^{Also in 1.103.8}

Changes

Deployment: Removed the eMudhra root CA from every certificate bundle the SDK, proxy and Docker images trust (#47670, #47969) ^{Also in 1.103.8}
Deployment: Changed the cosign key that signs Docker images and Helm charts to the one from commit e82a3c6 (#48103) ^{Also in 1.103.8}
Azure: Fixed Azure AI Foundry returning 400 when the client sends the dangerous-tool-use-2026-09-03 beta (#43934)
Chat completions: Fixed tool calls landing on choices[1] with gpt-5.4+ models, broken since v1.97.0 (#46099)
Messages API: Fixed /v1/messages streams holding message_start for minutes during adaptive thinking on Bedrock and Vertex, broken since v1.100.0 (#43600)
Token counting: Fixed DeepSeek and Qwen3.5 token counts running up to 30% low or twice too high on the count endpoints (#47685)
Token counting: Changed /v1/messages/count_tokens to return HTTP 400 instead of a known-wrong local estimate (#47705)
Caching: Fixed automatic prompt caching adding extra cache marks on /v1/messages when extra_body overrides a client mark (#43341)
Cost tracking and pricing: Fixed the Usage API timing out while looking up names for busy hashed keys (#43656)
Cost tracking and pricing: Fixed streamed requests through a model alias billing $0 instead of the deployment's price, broken since v1.92.0 (#44341)
Cost tracking and pricing: Fixed large non-streaming chat requests to openai/responses/* models logging and charging spend twice, broken since v1.102.0 (#44508)
Cost tracking and pricing: Fixed failed, timed-out, cancelled and spilled-over requests being priced wrong or not at all (#47718)
Cost tracking and pricing: Fixed batch cost tracking, claude-haiku-5-5 and Bedrock profile pricing, and safeguards requests on /v1/messages (#47726) ^{Also in 1.105.3}
Admin UI: Fixed Usage reports showing no owner for CLI session keys when spend logs are off or purged (#43642, #47805)

Backport #47802 · Backport #48076 · Full changelog