BerriAI/litellm v1.96.0-dev.2 on GitHub

Verify Docker Image Signature

All LiteLLM Docker images are signed with cosign. Every release is signed with the same key introduced in commit 0112e53.

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 original signing key:

cosign verify \
  --key https://raw.githubusercontent.com/BerriAI/litellm/0112e53046018d726492c814b3644b7d376029d0/cosign.pub \
  ghcr.io/berriai/litellm:v1.96.0-dev.2

Verify 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/v1.96.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.96.0-dev.2

Expected 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

What's Changed

fix(pricing): adjust gpt-5.6-terra and gpt-5.6-luna prices according to OpenAI's latest article by @lihugang in #35258
fix(caching): stamp provider on embedding cache-hit spend logs by @devin-ai-integration[bot] in #35282
fix(proxy): run post_call guardrails on /v1/messages streaming via unified guardrail translation by @mateo-berri in #35260
fix(fireworks_ai): correct Kimi K2.5/K2.6/K2.7 max output token limits by @devin-ai-integration[bot] in #35174
feat(mcp)!: extend keyless gateway OAuth flow to per-server MCP URL paths by @tin-berri in #34856
fix(proxy): request stream usage upstream by default and strip it from client streams by @mateo-berri in #35290
refactor(rate-limits): move the v3 limiter per-request stash off request metadata onto a ContextVar by @mateo-berri in #35278
test(e2e): skip the batch rate-limiter spend-row test pending LIT-5027 by @ryan-crabbe-berri in #35301
fix(guardrails/headroom): stop compressing the turn the model must act on by @tin-berri in #35294
fix(ui): let the internal user and org forms save sub-cent budgets by @ryan-crabbe-berri in #35302
fix(guardrails): serve config guardrails from list and info endpoints without a DB and make their ids stable by @mateo-berri in #35259
fix(anthropic): split mixed stream chunks by payload kind by @yucheng-berri in #35289
fix: give ComplexityRouter LLM classifier prior-turn context (LIT-4981) by @tin-berri in #35185
feat(spend-logs): mark the auto-router's own classifier calls by @tin-berri in #35300
fix(logging): bind litellm_metadata by reference in function_setup so guardrail info reaches spend logs by @yucheng-berri in #35292
feat(s3): support SSE-KMS encryption params on both S3 logging paths by @yucheng-berri in #35291
fix(policy_engine): preserve config-defined policies across DB sync and expose them via list APIs by @mateo-berri in #35263
test: fix order-dependent flake in passthrough guardrail call-type test by @mateo-berri in #35317
fix(pricing): correct gpt-5.6 prices for openai, bedrock, and flex long context by @mubashir1osmani in #35270
fix(cost): bill the fast service tier at the priority rate by @devin-ai-integration[bot] in #35320
fix(responses): map all documented in-stream error codes to real HTTP statuses by @mateo-berri in #35307
test(pricing): cover gpt-5.6 cache-cost plumbing and bedrock_mantle responses billing by @mateo-berri in #35324
chore: promote staging to main by @mateo-berri in #35328

New Contributors

@lihugang made their first contribution in #35258

Full Changelog: v1.96.0-dev.1...v1.96.0-dev.2