LiteLLM

AI

One OpenAI-shaped interface — and one proxy — in front of 100+ model providers.

Latest v1.96.0 · by BerriAIWebsiteBerriAI/litellm

Release activity

Release activity — 11 releases across 7 days since Jul 31, 2026. Each cell is one day; darker means more releases that day. Nothing is recorded before Jul 31, 2026. Older weeks are hidden at this screen width.
MayJunJulAug
SundayNo releases on Aug 2, 2026No releases on Aug 9, 2026
Monday2 releases on Aug 3, 20261 release on Aug 10, 2026
TuesdayNo releases on Aug 4, 2026No releases on Aug 11, 2026
Wednesday1 release on Aug 5, 2026
ThursdayNo releases on Aug 6, 2026
Friday3 releases on Jul 31, 20261 release on Aug 7, 2026
Saturday1 release on Aug 1, 20262 releases on Aug 8, 2026

11 releases since Jul 31, 2026, busiest day 3

Changelog

v1.96.0

Added 5
  • Add service_tier label to latency and spend metrics in Prometheus
  • Publish a generated JSON schema for model_prices_and_context_window.json
  • Split failed requests into their own series on the cache dashboard in UI
  • Add shareable log links via log_id query param on the logs page in UI
  • Add qwen3.7-plus and qwen3.7-max to the model cost map for dashscope
Fixed 15
  • Keep keep-alive connector config when an aiohttp session is rebuilt
  • Pin bundled postgres and redis to the bitnami legacy images in Helm
  • Decide rawPredict passthrough streaming from the request body for Vertex
  • Translate stop_sequences and disabled thinking for non-Claude targets in anthropic-adapter
  • Allow /v1/messages for JWT teams by default
  • Skip team model aliases that point at deleted deployments in proxy
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

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/cosign.pub \
  ghcr.io/berriai/litellm:v1.96.0

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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.95.0...v1.96.0

View originalPermalink
How v1.96.0 went

v1.97.0-rc.1

Pre-release
Added 3
  • Add apply_user_budget_to_team_keys opt-in in proxy
  • Show user email or alias in usage data export in ui
  • Track turns per complexity tier in auto-router
Fixed 16
  • Pass SSE-KMS key through to the batch input-file S3 upload in bedrock
  • Stop indexing choices[0] on choiceless streaming chunks in anthropic adapter
  • Normalize /v1/completions and /v1/responses batch records in bedrock
  • Return the real status code when a credential update is rejected in proxy
  • Improve Headroom /v1/compress HTTP 404 diagnostics in proxy
  • Invalidate cached project object on project update and delete in proxy
Security 1
  • Respect AZURE_AUTHORITY_HOST and derive the Azure Monitor audience per cloud in azure_sentinel
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:v1.97.0-rc.1

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/v1.97.0-rc.1/cosign.pub \
  ghcr.io/berriai/litellm:v1.97.0-rc.1

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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.97.0-dev.2...v1.97.0-rc.1

View originalPermalink
How v1.97.0-rc.1 went

v1.94.2

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:v1.94.2

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/v1.94.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.94.2

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

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.94.1...v1.94.2

View originalPermalink
How v1.94.2 went

v1.97.0-dev.2

Pre-release
Added 6
  • Add role capability gating to UI and migrate Tool Policies route
  • Make reminder marker pair configurable in auto-router
  • Derive a default auto-router savings baseline from the hardest tier in spend tracking
  • Let operators rename the four complexity tiers in complexity_router
  • Let operators replace the LLM classifier's system prompt in auto-router
  • Make the gateway middleware the source of truth for successful requests in SGR
Changed 2
  • Inject the fetch client's base URL instead of reading it at import in UI
  • Perform python, dashboard, and gen-api checks concurrently in pre-commit
Fixed 13
  • Name enable_jwt_auth when a JWT-shaped key is rejected
  • Update anthropic model presets in UI
  • Switch to the dashboard node floor via nvm or fnm in bootstrap
  • Self-heal handler clients closed after cache eviction
  • Keep OpenAI prompt cache token details through usage reassembly in cost tracking
  • Bill gpt-5.6 prompt cache reads at the cache read rate
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:v1.97.0-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/v1.97.0-dev.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.97.0-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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.97.0-dev.1...v1.97.0-dev.2

View originalPermalink
How v1.97.0-dev.2 went

v1.97.0-dev.1

Pre-release
Added 8
  • Resolve Cursor thinking/fast model-name suffixes on /cursor/chat/completions endpoint
  • Add non-streaming response toggle to playground
  • Apply default organization to new teams from default team settings
  • Expose session affinity configuration in the complexity router UI and default it to off
  • Add prompt moderation, response-text blocking, streaming buffer, and failure logging to Rubrik guardrails
  • Add custom metadata validation hook for team create and update
  • Add net auto-router savings to the cost-optimization dashboard
  • Show auto-router savings on the cost-optimization dashboard
Changed 1
  • Install hiredis so redis-py parses replies with its C parser
Fixed 14
  • Stop logging when disable_logging is called for team callbacks
  • Backfill null user_email on existing users during JWT auth
  • Block Playground page for viewer roles on direct URL access
  • Close evicted LLM clients so their connections are reclaimed
  • Apply key/team router_settings.model_group_alias
  • Read team callback dd_* params from kwargs instead of blocked dynamic params
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:v1.97.0-dev.1

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/v1.97.0-dev.1/cosign.pub \
  ghcr.io/berriai/litellm:v1.97.0-dev.1

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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.96.0-rc.1...v1.97.0-dev.1

View originalPermalink
How v1.97.0-dev.1 went

v1.95.0

Added 11
  • Track prompt compression saved tokens in daily spend aggregates
  • Route native Anthropic /messages through Rust behind LITELLM_RUST env var
  • Expose Anthropic Messages route (POST /v1/messages) on the axum gateway
  • Port OpenAI Responses API WebSockets to litellm-rust
  • Port BaseAWSLLM auth (credential resolution + SigV4) to litellm-core as a base provider
  • Add return_raw_model_name toggle for response model field in complexity-router
Changed 2
  • Migrate the litellm-rust workspace (core, ai-gateway, python-bridge) from Rust edition 2021 to edition 2024
  • Implement audio transcription via rust core (py->rust bridge) for Bedrock
Fixed 4
  • Treat malformed cost-map token limits as absent on /v1/models
  • Send v4 ingestion header for otel callback in Langfuse
  • Restore Content-Type application/json header for Fireworks AI (fixes 415)
  • Hide guardrail group headers when only one group has entries in UI
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:v1.95.0

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/v1.95.0/cosign.pub \
  ghcr.io/berriai/litellm:v1.95.0

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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.94.0...v1.95.0

View originalPermalink
How v1.95.0 went

v1.96.0-rc.1

Pre-release
Added 8
  • Expose classifier context window fields on Auto-Router screens
  • Add generic list handler for /management/v1
  • Source the ID-JAG subject from the user's stored SSO assertion
  • Add GET /management/v1/budgets
  • Show which log rows are the auto-router's own classifier calls
  • Add sorting, filtering and search to the budgets page
  • Add global exclude_metrics and exclude_labels options for prometheus
  • Let AI API keys read /model/info
Changed 1
  • Gate all mock testing request params behind a single config flag
Fixed 17
  • Annotate connected-app reachability on the gateway connect page
  • Recover the tool-name prefix boundary from registered prefixes
  • Exclude skipped tests from coverage-registry numerator
  • Deny MCP access when a named entitlement cannot be read
  • Dispose recycled client sessions deterministically
  • Run bedrock guardrail on MCP tool calls in during_mcp_call mode
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-rc.1

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-rc.1/cosign.pub \
  ghcr.io/berriai/litellm:v1.96.0-rc.1

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

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.96.0-dev.2...v1.96.0-rc.1

View originalPermalink
How v1.96.0-rc.1 went

v1.95.0-rc.3

Pre-release
Added 1
  • Send RFC 8707 resource indicators on upstream OAuth legs in MCP
Changed 2
  • Bump gitpython to 3.1.55 and brace-expansion to 5.0.8
  • Move the logs end-user filter onto /management/v1 endpoint
Fixed 16
  • Advertise 1M context window for Claude Opus 4.6+ on Azure AI Foundry
  • Resolve judge_model credentials via lazy Router lookup in llm_as_a_judge guardrails
  • Center vertical toolbar dividers in UI
  • Restore the Add MCP Server dialog size and header spacing in UI
  • Truncate long team names in the models table team dropdown in UI
  • Resolve dashboard base URL from environment instead of hardcoding localhost in e2e UI tests
Security 1
  • All LiteLLM Docker images are now signed with cosign for verification
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:v1.95.0-rc.3

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/v1.95.0-rc.3/cosign.pub \
  ghcr.io/berriai/litellm:v1.95.0-rc.3

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

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.95.0-rc.2...v1.95.0-rc.3

View originalPermalink
How v1.95.0-rc.3 went

v1.96.0-dev.2

Pre-release
Added 3
  • Extend keyless gateway OAuth flow to per-server MCP URL paths
  • Mark the auto-router's own classifier calls in spend logs
  • Support SSE-KMS encryption params on both S3 logging paths
Changed 1
  • Move the v3 limiter per-request stash off request metadata onto a ContextVar
Fixed 15
  • Adjust gpt-5.6-terra and gpt-5.6-luna prices according to OpenAI's latest article
  • Stamp provider on embedding cache-hit spend logs
  • Run post_call guardrails on /v1/messages streaming via unified guardrail translation
  • Correct Kimi K2.5/K2.6/K2.7 max output token limits for fireworks_ai
  • Request stream usage upstream by default and strip it from client streams
  • Stop compressing the turn the model must act on in guardrails/headroom
Security 1
  • Docker images are now signed with cosign for verification
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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.96.0-dev.1...v1.96.0-dev.2

View originalPermalink
How v1.96.0-dev.2 went

v1.95.0-rc.2

Pre-release
Added 12
  • Add Meta Model API provider and muse-spark-1.1
  • Add Azure GPT-5.6 (sol/terra/luna) pricing and metadata
  • Add /v1/messages to supported_endpoints schema enum
  • Add dcr_bridge column and plumbing for client-forwarded auth modes in MCP
  • Add shared composable DataTable component to UI
  • Relay upstream 401 on client-forwarded pass-through tool calls in MCP
Fixed 8
  • Mask credentials embedded in guardrail_response before persist
  • Honor store_prompts_in_spend_logs for guardrail_information in spend-logs
  • Sum multi-round session cost in logs UI
  • Stop persisting the DCR client onto true_passthrough and oauth_delegate server rows in MCP
  • Fail closed and surface semantic filter context window errors in MCP
  • Keep mid-conversation system messages in place for Claude Invoke in Bedrock
  • Add coordination_redis routes to component allowlist in proxy
  • Build redis usage cache from REDIS_* env when cache backend is not Redis in proxy
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:v1.95.0-rc.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/v1.95.0-rc.2/cosign.pub \
  ghcr.io/berriai/litellm:v1.95.0-rc.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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.93.0-dev.3...v1.95.0-rc.2

View originalPermalink
How v1.95.0-rc.2 went

v1.96.0-dev.1

Pre-release
Added 4
  • Add service_tier label to latency and spend metrics in Prometheus
  • Publish a generated JSON schema for model_prices_and_context_window.json
  • Split failed requests into their own series on the cache dashboard in UI
  • Add shareable log links via log_id query param on the logs page in UI
Fixed 15
  • Keep keep-alive connector config when an aiohttp session is rebuilt
  • Pin bundled postgres and redis to bitnamilegacy images in Helm
  • Decide rawPredict passthrough streaming from the request body for Vertex
  • Translate stop_sequences and disabled thinking for non-Claude targets in anthropic-adapter
  • Allow /v1/messages for JWT teams by default
  • Skip team model aliases that point at deleted deployments in proxy
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.1

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.1/cosign.pub \
  ghcr.io/berriai/litellm:v1.96.0-dev.1

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
New Contributors

Full Changelog: https://github.com/BerriAI/litellm/compare/v1.95.0-rc.1...v1.96.0-dev.1

View originalPermalink
How v1.96.0-dev.1 went

More in AI

View all
codex

codex release notes.

codex
Ollama

Get up and running with large language models locally.

Ollama
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

openclaw
superpowers

An agentic skills framework & software development methodology that works.

obra
ECC

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

affaan-m
hermes-agent

The agent that grows with you

NousResearch

Discussion