v1.79.1.rc.1

What's Changed

• 1-79-0 docs by @ishaan-jaff in #15936
• feat(lasso): Upgrade to Lasso API v3 and fix ULID generation by @oroxenberg in #15941
• Enable OpenTelemetry context propagation by external tracers by @eycjur in #15940
• Fix documentation for videos by @Sameerlite in #15937
• Fix duplicate trace in langfuse_otel by @eycjur in #15931
• [Feat] add support for dynamic client registration by @uc4w6c in #15921
• Update IBM Guardrails to correctly use SSL Verify argument by @RobGeada in #15975
• feat: support during_call for model armor guardrails by @bjornjee in #15970
• docs(openrouter): add base_url config with environment variables by @shanto12 in #15946
• [Buf fix] - Azure OpenAI, fix ContextWindowExceededError is not mapped from Azure openai errors by @ishaan-jaff in #15981
• [Fix] DD logging - ensure key's metadata + guardrail is logged on DD by @ishaan-jaff in #15980
• [Feat] OTEL - Ensure error information is logged on OTEL by @ishaan-jaff in #15978
• [Fix] Minor fix proxy - ensure User API key and team id and user id missing from custom callback is not misfiring by @ishaan-jaff in #15982
• [Fix] Azure OpenAI - Add handling for v1 under azure api versions by @ishaan-jaff in #15984
• Fix: Respect LiteLLM-Disable-Message-Redaction header for Responses API by @Sameerlite in #15966
• [Feat] UI - Changed API Base from Select to Input in New LLM Credentials by @yuneng-jiang in #15987
• [Bug Fix] Remove limit from admin UI numerical input fix by @yuneng-jiang in #15991
• [Feature] UI - Key Already Exist Error Notification by @yuneng-jiang in #15993
• [Fix] - Responses API - add /openai routes for responses API. (Azure OpenAI SDK Compatibility) by @ishaan-jaff in #15988
• Add deprecation dates for models by @dima-hx430 in #15976
• docs(guardrails/ibm_guardrails): add additional detail to ibm_guardrails.md by @m-misiura in #15971
• Perf speed up pytest by @uc4w6c in #15951
• fix: Preserve Bedrock inference profile IDs in health checks by @ylgibby in #15947
• Fix: Support tool usage messages with Langfuse OTEL integration by @eycjur in #15932
• Add Haiku 4.5 pricing for open router by @Somtom in #15909
• fix(opik): enhance requester metadata retrieval from API key auth by @Thomas-Mildner in #15897
• [feat]: graceful degradation for pillar service when using litellm by @afogel in #15857
• Add GitlabPromptCache and enable subfolder access by @deepanshululla in #15712
• Add OpenAI client usage documentation for videos and fix navigation visibility by @Sameerlite in #15996
• [Feature] Config Models should not be editable by @yuneng-jiang in #16020
• [Fix] Guardrails - Ensure Key Guardrails are applied by @ishaan-jaff in #16025
• [UI] Feature - Add Apply Guardrail Testing Playground by @ishaan-jaff in #16030
• [Fix] SQS Logger - Add Base64 handling by @ishaan-jaff in #16028
• Fix mutation of original request for gemini request by @Sameerlite in #16002
• Fix: Redact reasoning summaries in ResponsesAPI output when message logging is disabled by @Sameerlite in #15965
• fix: Support text.format parameter in Responses API for providers without native ResponsesAPIConfig by @rodolfo-nobrega in #16023
• Remove unnecessary model variable assignment by @Mte90 in #16008
• Add license metadata to health/readiness endpoint. by @bernata in #15997
• chore(deps): bump hono from 4.9.7 to 4.10.3 in /litellm-js/spend-logs by @dependabot[bot] in #15915
• docs: improve Grayswan guardrail documentation by @TeddyAmkie in #15875
• fix(apscheduler): prevent memory leaks from jitter and frequent job intervals by @jatorre in #15846
• Python entry-point for CustomLLM subclasses by @AlbertDeFusco in #15881
• Allow using ARNs when generation images via Bedrock by @komarovd95 in #15789
• Added fallback logic for detecting file content-type when S3 returns generic by @langpingxue in #15635
• fix: prevent httpx DeprecationWarning memory leak in AsyncHTTPHandler by @AlexsanderHamir in #16024
• [Feat] Add FAL AI Image Generations on LiteLLM by @ishaan-jaff in #16067
• Feat: Mistral API - add codestral-embed-2505 by @ishaan-jaff in #16071
• Fix spend tracking for OCR/aOCR requests (log pages_processed + recognize OCRResponse) by @OrionCodeDev in #16070
• [Feat] Add support for Batch API Rate limiting - PR1 adds support for input based rate limits by @ishaan-jaff in #16075
• [Feature] UI - Validation for Proxy Base URL in SSO Settings by @yuneng-jiang in #16082
• [Feature] UI - Test Key UI Embeddings by @yuneng-jiang in #16065
• [Feature] UI - Add Key Type Select in Key Settings by @yuneng-jiang in #16034
• feat(guardrails): Add per-request profile overrides to PANW Prisma AIRS by @jroberts2600 in #16069
• docs: use custom-llm-provider header in examples by @tlecomte in #16055
• Improve(mcp): respect X-Forwarded- headers in OAuth endpoints by @talalryz in #16036
• Add OpenAI-compatible annotations support for Cohere v2 citations by @Sameerlite in #16038
• Opik user auth key metadata Documentation by @Thomas-Mildner in #16004
• [Fix] Circle CI UI E2E Test Fix by @yuneng-jiang in #16100
• Fix: Moderations endpoint now respects api_base configuration parameter by @Sameerlite in #16087
• [Infra] Litellm Backend SSO Changes by @yuneng-jiang in #16029
• Litellm docs readme fixes by @ishaan-jaff in #16107
• [Docs] readme fixes add supported providers by @ishaan-jaff in #16109
• Add gemini/gemini-embedding-001 pricing entry for Google GenAI API by @sbinnee in #16078
• Add supports vision field, to qwen-vl models, in model_prices_and_context_window.json by @JetoPistola in #16106
• feat: handle Deepgram detected language when available by @gvioss in #16093
• Fix vercel_ai_gateway entry for glm-4.6 by @pale-aura in #16084
• Add OCI Signer Authentication. Closes #16048, Closes #15654 by @gotsysdba in #16064
• Changes to fix frequency_penalty and presence_penalty issue for gemini-2.5-pro model by @tanvithakur94 in #16041
• Add Add per model group header forwarding for Bedrock Invoke API by @Sameerlite in #16042
• fix: Handle multiple rate limit types per descriptor and prevent IndexError by @orolega in #16039
• prompt_caching.md: Fix wrong prompt_tokens definition by @li-boxuan in #16044
• Add Xai websearch cost by @Sameerlite in #16001
• Don't add "accounts/fireworks/models" prefix for Fireworks Provider by @1stprinciple in #15938
• fix: make debug log debug by @raghav-stripe in #16137
• [Feat] UI + Management - Allow setting all routing strategies, tag filtering on UI by @ishaan-jaff in #16139
• [Feature] UI - Add tags in model creation by @yuneng-jiang in #16138
• [Feature] UI - Add Tags to update model by @yuneng-jiang in #16140
• [Feature] UI - Config Guardrails should not be editable and guardrail info fix by @yuneng-jiang in #16142
• [Feat] UI - Allow setting cache settings on UI by @ishaan-jaff in #16143
• build(deps): bump starlette from 0.47.2 to 0.49.1 by @dependabot[bot] in https://github.com/BerriAI/lite...

v1.79.1-nightly

What's Changed

• 1-79-0 docs by @ishaan-jaff in #15936
• feat(lasso): Upgrade to Lasso API v3 and fix ULID generation by @oroxenberg in #15941
• Enable OpenTelemetry context propagation by external tracers by @eycjur in #15940
• Fix documentation for videos by @Sameerlite in #15937
• Fix duplicate trace in langfuse_otel by @eycjur in #15931
• [Feat] add support for dynamic client registration by @uc4w6c in #15921
• Update IBM Guardrails to correctly use SSL Verify argument by @RobGeada in #15975
• feat: support during_call for model armor guardrails by @bjornjee in #15970
• docs(openrouter): add base_url config with environment variables by @shanto12 in #15946
• [Buf fix] - Azure OpenAI, fix ContextWindowExceededError is not mapped from Azure openai errors by @ishaan-jaff in #15981
• [Fix] DD logging - ensure key's metadata + guardrail is logged on DD by @ishaan-jaff in #15980
• [Feat] OTEL - Ensure error information is logged on OTEL by @ishaan-jaff in #15978
• [Fix] Minor fix proxy - ensure User API key and team id and user id missing from custom callback is not misfiring by @ishaan-jaff in #15982
• [Fix] Azure OpenAI - Add handling for v1 under azure api versions by @ishaan-jaff in #15984
• Fix: Respect LiteLLM-Disable-Message-Redaction header for Responses API by @Sameerlite in #15966
• [Feat] UI - Changed API Base from Select to Input in New LLM Credentials by @yuneng-jiang in #15987
• [Bug Fix] Remove limit from admin UI numerical input fix by @yuneng-jiang in #15991
• [Feature] UI - Key Already Exist Error Notification by @yuneng-jiang in #15993
• [Fix] - Responses API - add /openai routes for responses API. (Azure OpenAI SDK Compatibility) by @ishaan-jaff in #15988
• Add deprecation dates for models by @dima-hx430 in #15976
• docs(guardrails/ibm_guardrails): add additional detail to ibm_guardrails.md by @m-misiura in #15971
• Perf speed up pytest by @uc4w6c in #15951
• fix: Preserve Bedrock inference profile IDs in health checks by @ylgibby in #15947
• Fix: Support tool usage messages with Langfuse OTEL integration by @eycjur in #15932
• Add Haiku 4.5 pricing for open router by @Somtom in #15909
• fix(opik): enhance requester metadata retrieval from API key auth by @Thomas-Mildner in #15897
• [feat]: graceful degradation for pillar service when using litellm by @afogel in #15857
• Add GitlabPromptCache and enable subfolder access by @deepanshululla in #15712
• Add OpenAI client usage documentation for videos and fix navigation visibility by @Sameerlite in #15996
• [Feature] Config Models should not be editable by @yuneng-jiang in #16020
• [Fix] Guardrails - Ensure Key Guardrails are applied by @ishaan-jaff in #16025
• [UI] Feature - Add Apply Guardrail Testing Playground by @ishaan-jaff in #16030
• [Fix] SQS Logger - Add Base64 handling by @ishaan-jaff in #16028
• Fix mutation of original request for gemini request by @Sameerlite in #16002
• Fix: Redact reasoning summaries in ResponsesAPI output when message logging is disabled by @Sameerlite in #15965
• fix: Support text.format parameter in Responses API for providers without native ResponsesAPIConfig by @rodolfo-nobrega in #16023
• Remove unnecessary model variable assignment by @Mte90 in #16008
• Add license metadata to health/readiness endpoint. by @bernata in #15997
• chore(deps): bump hono from 4.9.7 to 4.10.3 in /litellm-js/spend-logs by @dependabot[bot] in #15915
• docs: improve Grayswan guardrail documentation by @TeddyAmkie in #15875
• fix(apscheduler): prevent memory leaks from jitter and frequent job intervals by @jatorre in #15846
• Python entry-point for CustomLLM subclasses by @AlbertDeFusco in #15881
• Allow using ARNs when generation images via Bedrock by @komarovd95 in #15789
• Added fallback logic for detecting file content-type when S3 returns generic by @langpingxue in #15635
• fix: prevent httpx DeprecationWarning memory leak in AsyncHTTPHandler by @AlexsanderHamir in #16024
• [Feat] Add FAL AI Image Generations on LiteLLM by @ishaan-jaff in #16067
• Feat: Mistral API - add codestral-embed-2505 by @ishaan-jaff in #16071
• Fix spend tracking for OCR/aOCR requests (log pages_processed + recognize OCRResponse) by @OrionCodeDev in #16070
• [Feat] Add support for Batch API Rate limiting - PR1 adds support for input based rate limits by @ishaan-jaff in #16075
• [Feature] UI - Validation for Proxy Base URL in SSO Settings by @yuneng-jiang in #16082
• [Feature] UI - Test Key UI Embeddings by @yuneng-jiang in #16065
• [Feature] UI - Add Key Type Select in Key Settings by @yuneng-jiang in #16034
• feat(guardrails): Add per-request profile overrides to PANW Prisma AIRS by @jroberts2600 in #16069
• docs: use custom-llm-provider header in examples by @tlecomte in #16055
• Improve(mcp): respect X-Forwarded- headers in OAuth endpoints by @talalryz in #16036
• Add OpenAI-compatible annotations support for Cohere v2 citations by @Sameerlite in #16038
• Opik user auth key metadata Documentation by @Thomas-Mildner in #16004
• [Fix] Circle CI UI E2E Test Fix by @yuneng-jiang in #16100
• Fix: Moderations endpoint now respects api_base configuration parameter by @Sameerlite in #16087
• [Infra] Litellm Backend SSO Changes by @yuneng-jiang in #16029
• Litellm docs readme fixes by @ishaan-jaff in #16107
• [Docs] readme fixes add supported providers by @ishaan-jaff in #16109
• Add gemini/gemini-embedding-001 pricing entry for Google GenAI API by @sbinnee in #16078
• Add supports vision field, to qwen-vl models, in model_prices_and_context_window.json by @JetoPistola in #16106
• feat: handle Deepgram detected language when available by @gvioss in #16093
• Fix vercel_ai_gateway entry for glm-4.6 by @pale-aura in #16084
• Add OCI Signer Authentication. Closes #16048, Closes #15654 by @gotsysdba in #16064
• Changes to fix frequency_penalty and presence_penalty issue for gemini-2.5-pro model by @tanvithakur94 in #16041
• Add Add per model group header forwarding for Bedrock Invoke API by @Sameerlite in #16042
• fix: Handle multiple rate limit types per descriptor and prevent IndexError by @orolega in #16039
• prompt_caching.md: Fix wrong prompt_tokens definition by @li-boxuan in #16044
• Add Xai websearch cost by @Sameerlite in #16001
• Don't add "accounts/fireworks/models" prefix for Fireworks Provider by @1stprinciple in #15938
• fix: make debug log debug by @raghav-stripe in #16137
• [Feat] UI + Management - Allow setting all routing strategies, tag filtering on UI by @ishaan-jaff in #16139
• [Feature] UI - Add tags in model creation by @yuneng-jiang in #16138
• [Feature] UI - Add Tags to update model by @yuneng-jiang in #16140
• [Feature] UI - Config Guardrails should not be editable and guardrail info fix by @yuneng-jiang in #16142
• [Feat] UI - Allow setting cache settings on UI by @ishaan-jaff in #16143
• build(deps): bump starlette from 0.47.2 to 0.49.1 by @dependabot[bot] in https://github.com/BerriAI/lite...

v1.79.0-stable

Full Changelog: v1.79.0-nightly...v1.79.0-stable

v1.78.5.rc.4

Full Changelog: v1.78.5-nightly...v1.78.5.rc.4

v1.79.1.dev1

What's Changed

• 1-79-0 docs by @ishaan-jaff in #15936
• feat(lasso): Upgrade to Lasso API v3 and fix ULID generation by @oroxenberg in #15941
• Enable OpenTelemetry context propagation by external tracers by @eycjur in #15940
• Fix documentation for videos by @Sameerlite in #15937
• Fix duplicate trace in langfuse_otel by @eycjur in #15931
• [Feat] add support for dynamic client registration by @uc4w6c in #15921
• Update IBM Guardrails to correctly use SSL Verify argument by @RobGeada in #15975
• feat: support during_call for model armor guardrails by @bjornjee in #15970
• docs(openrouter): add base_url config with environment variables by @shanto12 in #15946
• [Buf fix] - Azure OpenAI, fix ContextWindowExceededError is not mapped from Azure openai errors by @ishaan-jaff in #15981
• [Fix] DD logging - ensure key's metadata + guardrail is logged on DD by @ishaan-jaff in #15980
• [Feat] OTEL - Ensure error information is logged on OTEL by @ishaan-jaff in #15978
• [Fix] Minor fix proxy - ensure User API key and team id and user id missing from custom callback is not misfiring by @ishaan-jaff in #15982
• [Fix] Azure OpenAI - Add handling for v1 under azure api versions by @ishaan-jaff in #15984
• Fix: Respect LiteLLM-Disable-Message-Redaction header for Responses API by @Sameerlite in #15966
• [Feat] UI - Changed API Base from Select to Input in New LLM Credentials by @yuneng-jiang in #15987
• [Bug Fix] Remove limit from admin UI numerical input fix by @yuneng-jiang in #15991
• [Feature] UI - Key Already Exist Error Notification by @yuneng-jiang in #15993
• [Fix] - Responses API - add /openai routes for responses API. (Azure OpenAI SDK Compatibility) by @ishaan-jaff in #15988
• Add deprecation dates for models by @dima-hx430 in #15976
• docs(guardrails/ibm_guardrails): add additional detail to ibm_guardrails.md by @m-misiura in #15971
• Perf speed up pytest by @uc4w6c in #15951
• fix: Preserve Bedrock inference profile IDs in health checks by @ylgibby in #15947
• Fix: Support tool usage messages with Langfuse OTEL integration by @eycjur in #15932
• Add Haiku 4.5 pricing for open router by @Somtom in #15909
• fix(opik): enhance requester metadata retrieval from API key auth by @Thomas-Mildner in #15897
• [feat]: graceful degradation for pillar service when using litellm by @afogel in #15857
• Add GitlabPromptCache and enable subfolder access by @deepanshululla in #15712
• Add OpenAI client usage documentation for videos and fix navigation visibility by @Sameerlite in #15996
• [Feature] Config Models should not be editable by @yuneng-jiang in #16020
• [Fix] Guardrails - Ensure Key Guardrails are applied by @ishaan-jaff in #16025
• [UI] Feature - Add Apply Guardrail Testing Playground by @ishaan-jaff in #16030
• [Fix] SQS Logger - Add Base64 handling by @ishaan-jaff in #16028
• Fix mutation of original request for gemini request by @Sameerlite in #16002
• Fix: Redact reasoning summaries in ResponsesAPI output when message logging is disabled by @Sameerlite in #15965
• fix: Support text.format parameter in Responses API for providers without native ResponsesAPIConfig by @rodolfo-nobrega in #16023
• Remove unnecessary model variable assignment by @Mte90 in #16008
• Add license metadata to health/readiness endpoint. by @bernata in #15997
• chore(deps): bump hono from 4.9.7 to 4.10.3 in /litellm-js/spend-logs by @dependabot[bot] in #15915
• docs: improve Grayswan guardrail documentation by @TeddyAmkie in #15875
• fix(apscheduler): prevent memory leaks from jitter and frequent job intervals by @jatorre in #15846
• Python entry-point for CustomLLM subclasses by @AlbertDeFusco in #15881
• Allow using ARNs when generation images via Bedrock by @komarovd95 in #15789
• Added fallback logic for detecting file content-type when S3 returns generic by @langpingxue in #15635
• fix: prevent httpx DeprecationWarning memory leak in AsyncHTTPHandler by @AlexsanderHamir in #16024
• [Feat] Add FAL AI Image Generations on LiteLLM by @ishaan-jaff in #16067
• Feat: Mistral API - add codestral-embed-2505 by @ishaan-jaff in #16071
• Fix spend tracking for OCR/aOCR requests (log pages_processed + recognize OCRResponse) by @OrionCodeDev in #16070
• [Feat] Add support for Batch API Rate limiting - PR1 adds support for input based rate limits by @ishaan-jaff in #16075
• [Feature] UI - Validation for Proxy Base URL in SSO Settings by @yuneng-jiang in #16082
• [Feature] UI - Test Key UI Embeddings by @yuneng-jiang in #16065
• [Feature] UI - Add Key Type Select in Key Settings by @yuneng-jiang in #16034
• feat(guardrails): Add per-request profile overrides to PANW Prisma AIRS by @jroberts2600 in #16069
• docs: use custom-llm-provider header in examples by @tlecomte in #16055
• Improve(mcp): respect X-Forwarded- headers in OAuth endpoints by @talalryz in #16036
• Add OpenAI-compatible annotations support for Cohere v2 citations by @Sameerlite in #16038
• Opik user auth key metadata Documentation by @Thomas-Mildner in #16004
• [Fix] Circle CI UI E2E Test Fix by @yuneng-jiang in #16100
• Fix: Moderations endpoint now respects api_base configuration parameter by @Sameerlite in #16087
• [Infra] Litellm Backend SSO Changes by @yuneng-jiang in #16029

New Contributors

• @RobGeada made their first contribution in #15975
• @shanto12 made their first contribution in #15946
• @dima-hx430 made their first contribution in #15976
• @m-misiura made their first contribution in #15971
• @ylgibby made their first contribution in #15947
• @Somtom made their first contribution in #15909
• @rodolfo-nobrega made their first contribution in #16023
• @bernata made their first contribution in #15997
• @AlbertDeFusco made their first contribution in #15881
• @komarovd95 made their first contribution in #15789
• @langpingxue made their first contribution in #15635
• @OrionCodeDev made their first contribution in #16070

Full Changelog: v1.79.0-nightly...v1.79.1.dev1

v1.77.7.dev3

What's Changed

• 1-79-0 docs by @ishaan-jaff in #15936
• feat(lasso): Upgrade to Lasso API v3 and fix ULID generation by @oroxenberg in #15941
• Enable OpenTelemetry context propagation by external tracers by @eycjur in #15940
• Fix documentation for videos by @Sameerlite in #15937
• Fix duplicate trace in langfuse_otel by @eycjur in #15931
• [Feat] add support for dynamic client registration by @uc4w6c in #15921
• Update IBM Guardrails to correctly use SSL Verify argument by @RobGeada in #15975
• feat: support during_call for model armor guardrails by @bjornjee in #15970
• docs(openrouter): add base_url config with environment variables by @shanto12 in #15946
• [Buf fix] - Azure OpenAI, fix ContextWindowExceededError is not mapped from Azure openai errors by @ishaan-jaff in #15981
• [Fix] DD logging - ensure key's metadata + guardrail is logged on DD by @ishaan-jaff in #15980
• [Feat] OTEL - Ensure error information is logged on OTEL by @ishaan-jaff in #15978
• [Fix] Minor fix proxy - ensure User API key and team id and user id missing from custom callback is not misfiring by @ishaan-jaff in #15982
• [Fix] Azure OpenAI - Add handling for v1 under azure api versions by @ishaan-jaff in #15984
• Fix: Respect LiteLLM-Disable-Message-Redaction header for Responses API by @Sameerlite in #15966
• [Feat] UI - Changed API Base from Select to Input in New LLM Credentials by @yuneng-jiang in #15987
• [Bug Fix] Remove limit from admin UI numerical input fix by @yuneng-jiang in #15991
• [Feature] UI - Key Already Exist Error Notification by @yuneng-jiang in #15993
• [Fix] - Responses API - add /openai routes for responses API. (Azure OpenAI SDK Compatibility) by @ishaan-jaff in #15988
• Add deprecation dates for models by @dima-hx430 in #15976
• docs(guardrails/ibm_guardrails): add additional detail to ibm_guardrails.md by @m-misiura in #15971
• Perf speed up pytest by @uc4w6c in #15951
• fix: Preserve Bedrock inference profile IDs in health checks by @ylgibby in #15947
• Fix: Support tool usage messages with Langfuse OTEL integration by @eycjur in #15932
• Add Haiku 4.5 pricing for open router by @Somtom in #15909
• fix(opik): enhance requester metadata retrieval from API key auth by @Thomas-Mildner in #15897
• [feat]: graceful degradation for pillar service when using litellm by @afogel in #15857
• Add GitlabPromptCache and enable subfolder access by @deepanshululla in #15712
• Add OpenAI client usage documentation for videos and fix navigation visibility by @Sameerlite in #15996
• [Feature] Config Models should not be editable by @yuneng-jiang in #16020
• [Fix] Guardrails - Ensure Key Guardrails are applied by @ishaan-jaff in #16025
• [UI] Feature - Add Apply Guardrail Testing Playground by @ishaan-jaff in #16030
• [Fix] SQS Logger - Add Base64 handling by @ishaan-jaff in #16028
• Fix mutation of original request for gemini request by @Sameerlite in #16002
• Fix: Redact reasoning summaries in ResponsesAPI output when message logging is disabled by @Sameerlite in #15965
• fix: Support text.format parameter in Responses API for providers without native ResponsesAPIConfig by @rodolfo-nobrega in #16023
• Remove unnecessary model variable assignment by @Mte90 in #16008
• Add license metadata to health/readiness endpoint. by @bernata in #15997
• chore(deps): bump hono from 4.9.7 to 4.10.3 in /litellm-js/spend-logs by @dependabot[bot] in #15915
• docs: improve Grayswan guardrail documentation by @TeddyAmkie in #15875
• fix(apscheduler): prevent memory leaks from jitter and frequent job intervals by @jatorre in #15846
• Python entry-point for CustomLLM subclasses by @AlbertDeFusco in #15881
• Allow using ARNs when generation images via Bedrock by @komarovd95 in #15789
• Added fallback logic for detecting file content-type when S3 returns generic by @langpingxue in #15635
• fix: prevent httpx DeprecationWarning memory leak in AsyncHTTPHandler by @AlexsanderHamir in #16024
• [Feat] Add FAL AI Image Generations on LiteLLM by @ishaan-jaff in #16067
• Feat: Mistral API - add codestral-embed-2505 by @ishaan-jaff in #16071

New Contributors

• @RobGeada made their first contribution in #15975
• @shanto12 made their first contribution in #15946
• @dima-hx430 made their first contribution in #15976
• @m-misiura made their first contribution in #15971
• @ylgibby made their first contribution in #15947
• @Somtom made their first contribution in #15909
• @rodolfo-nobrega made their first contribution in #16023
• @bernata made their first contribution in #15997
• @AlbertDeFusco made their first contribution in #15881
• @komarovd95 made their first contribution in #15789
• @langpingxue made their first contribution in #15635

Full Changelog: v1.79.0-nightly...v1.77.7.dev3

v1.77.7.dev2

Full Changelog: v1.77.7-stable...v1.77.7.dev2

v1.79.0.rc.1

What's Changed

• [Bug Fix]: ErrorEvent ValidationError when OpenAI Responses API returns nested error structure by @ishaan-jaff in #15804
• [Fix] Azure AI Speech - Ensure voice is mapped from request body -> SSML body , allow sending role and style by @ishaan-jaff in #15810
• Use proper bedrock model name in health check by @nuernber in #15808
• [Feat] Add DataforSEO Search API by @ishaan-jaff in #15817
• [Feat] Add Google PSE Search Provider by @ishaan-jaff in #15816
• [Feat] Add cost tracking for Search API requests - Google PSE, Tavily, Parallel AI, Exa AI by @ishaan-jaff in #15821
• (feat) Vector Stores: support Vertex AI Search API as vector store through LiteLLM by @krrishdholakia in #15781
• fix(responses-api): simplify reasoning item handling for gpt-5-codex by @AlexsanderHamir in #15815
• fix: replace deprecated gemini-1.5-pro-preview-0514 by @AlexsanderHamir in #15852
• [Bug Fix]: Hooks broken on /bedrock passthrough due to missing metadata by @ishaan-jaff in #15849
• [Bug Fix] Exa Search API - ensure request params are sent to Exa AI by @ishaan-jaff in #15855
• fix(vertex-ai): cost tracking for search spend by @mythral in #15859
• fix(ui/): fix routing for custom server root path by @krrishdholakia in #15701
• [fix] Pass user-defined headers and extra_headers to image-edit calls by @byrongrogan in #15811
• [Feat] - [Backend] Search APIs - Allow storing configured Search APIs in DB by @ishaan-jaff in #15862
• [Feat] UI - Search Tools, allow adding search tools on UI + testing search by @ishaan-jaff in #15871
• [Feat] UI - Add logos for search providers by @ishaan-jaff in #15872
• docs: add responses api on openai docs by @mubashirosmani in #15866
• docs: add OpenAI responses api by @mubashirosmani in #15868
• feat(proxy): support absolute RPM/TPM in priority_reservation by @AlexsanderHamir in #15813
• Add documentation for enable_caching_on_provider_specific_optional_params setting by @Sameerlite in #15885
• Implement Bedrock Guardrail apply_guardrail endpoint support by @Sameerlite in #15892
• Lasso Security Guardrail: Add v3 API Support by @oroxenberg in #12452
• Litellm sameer oct staging by @Sameerlite in #15806
• fix: minimize the occurrence of deadlocks by @CAFxX in #15281
• Fix MLFlow tags - split request_tags into (key, val) if request_tag has colon by @reflection in #15914
• Add mistral medium 3 and Codestral 2 on vertex by @superpoussin22 in #15887
• fixed lasso import config, redis cluster hash tags for test keys by @shadielfares in #15917
• update vertex ai gemini costs by @otaviofbrito in #15911
• [Feat] New Guardrail - Dynamo AI Guardrail by @ishaan-jaff in #15920
• (feat) Organizations: allow org admins to create teams on UI + (feat) IBM Guardrails by @krrishdholakia in #15924
• fix(managed_files.py): don't raise error if managed object is not found + (Feat) Azure AI - Search Vector Stores + (Fix) Batches - “User default_user_id does not have access to the object” when object not in db + (fix) Vector Stores - show config.yaml vector stores on UI by @krrishdholakia in #15873
• Responses API - support tags in metadata by @krrishdholakia in #15867
• VertexAI Search Vector Store - Passthrough endpoint support + Vector store search Cost tracking support by @krrishdholakia in #15824
• Guardrails - Responses API, Image Gen, Text completions, Audio transcriptions, Audio Speech, Rerank, Anthropic Messages API support via the unified apply_guardrails function by @krrishdholakia in #15706
• Org level tpm/rpm limits + Team tpm/rpm validation when assigned to org by @krrishdholakia in #15549
• (security) Responses API - prevent User A from retrieving User B's response, if response.id is leaked by @krrishdholakia in #15757
• fix(opentelemetry.py): fix issue where headers were not being split correctly + feat(bedrock): add titan image generations w/ cost tracking by @krrishdholakia in #15916

New Contributors

• @mythral made their first contribution in #15859
• @mubashirosmani made their first contribution in #15866
• @CAFxX made their first contribution in #15281
• @reflection made their first contribution in #15914
• @shadielfares made their first contribution in #15917

Full Changelog: v1.78.7-nightly...v1.79.0.rc.1

v1.79.0-nightly

What's Changed

• [Bug Fix]: ErrorEvent ValidationError when OpenAI Responses API returns nested error structure by @ishaan-jaff in #15804
• [Fix] Azure AI Speech - Ensure voice is mapped from request body -> SSML body , allow sending role and style by @ishaan-jaff in #15810
• Use proper bedrock model name in health check by @nuernber in #15808
• [Feat] Add DataforSEO Search API by @ishaan-jaff in #15817
• [Feat] Add Google PSE Search Provider by @ishaan-jaff in #15816
• [Feat] Add cost tracking for Search API requests - Google PSE, Tavily, Parallel AI, Exa AI by @ishaan-jaff in #15821
• (feat) Vector Stores: support Vertex AI Search API as vector store through LiteLLM by @krrishdholakia in #15781
• fix(responses-api): simplify reasoning item handling for gpt-5-codex by @AlexsanderHamir in #15815
• fix: replace deprecated gemini-1.5-pro-preview-0514 by @AlexsanderHamir in #15852
• [Bug Fix]: Hooks broken on /bedrock passthrough due to missing metadata by @ishaan-jaff in #15849
• [Bug Fix] Exa Search API - ensure request params are sent to Exa AI by @ishaan-jaff in #15855
• fix(vertex-ai): cost tracking for search spend by @mythral in #15859
• fix(ui/): fix routing for custom server root path by @krrishdholakia in #15701
• [fix] Pass user-defined headers and extra_headers to image-edit calls by @byrongrogan in #15811
• [Feat] - [Backend] Search APIs - Allow storing configured Search APIs in DB by @ishaan-jaff in #15862
• [Feat] UI - Search Tools, allow adding search tools on UI + testing search by @ishaan-jaff in #15871
• [Feat] UI - Add logos for search providers by @ishaan-jaff in #15872
• docs: add responses api on openai docs by @mubashirosmani in #15866
• docs: add OpenAI responses api by @mubashirosmani in #15868
• feat(proxy): support absolute RPM/TPM in priority_reservation by @AlexsanderHamir in #15813
• Add documentation for enable_caching_on_provider_specific_optional_params setting by @Sameerlite in #15885
• Implement Bedrock Guardrail apply_guardrail endpoint support by @Sameerlite in #15892
• Lasso Security Guardrail: Add v3 API Support by @oroxenberg in #12452
• Litellm sameer oct staging by @Sameerlite in #15806
• fix: minimize the occurrence of deadlocks by @CAFxX in #15281
• Fix MLFlow tags - split request_tags into (key, val) if request_tag has colon by @reflection in #15914
• Add mistral medium 3 and Codestral 2 on vertex by @superpoussin22 in #15887
• fixed lasso import config, redis cluster hash tags for test keys by @shadielfares in #15917
• update vertex ai gemini costs by @otaviofbrito in #15911
• [Feat] New Guardrail - Dynamo AI Guardrail by @ishaan-jaff in #15920
• (feat) Organizations: allow org admins to create teams on UI + (feat) IBM Guardrails by @krrishdholakia in #15924
• fix(managed_files.py): don't raise error if managed object is not found + (Feat) Azure AI - Search Vector Stores + (Fix) Batches - “User default_user_id does not have access to the object” when object not in db + (fix) Vector Stores - show config.yaml vector stores on UI by @krrishdholakia in #15873
• Responses API - support tags in metadata by @krrishdholakia in #15867
• VertexAI Search Vector Store - Passthrough endpoint support + Vector store search Cost tracking support by @krrishdholakia in #15824
• Guardrails - Responses API, Image Gen, Text completions, Audio transcriptions, Audio Speech, Rerank, Anthropic Messages API support via the unified apply_guardrails function by @krrishdholakia in #15706
• Org level tpm/rpm limits + Team tpm/rpm validation when assigned to org by @krrishdholakia in #15549
• (security) Responses API - prevent User A from retrieving User B's response, if response.id is leaked by @krrishdholakia in #15757
• fix(opentelemetry.py): fix issue where headers were not being split correctly + feat(bedrock): add titan image generations w/ cost tracking by @krrishdholakia in #15916

New Contributors

• @mythral made their first contribution in #15859
• @mubashirosmani made their first contribution in #15866
• @CAFxX made their first contribution in #15281
• @reflection made their first contribution in #15914
• @shadielfares made their first contribution in #15917

Full Changelog: v1.78.7-nightly...v1.79.0-nightly

v1.78.7-nightly

What's Changed

• fix: Add response_type + PKCE parameters to OAuth authorization endpoint by @talalryz in #15720
• feat: add GraySwan Guardrails support by @uc4w6c in #15756
• [Docs] Add Azure AI - OCR to docs by @ishaan-jaff in #15768
• Auth Header Fix for MCP Tool Call by @1vinodsingh1 in #15736
• chore: rename GraySwan to Gray Swan by @uc4w6c in #15771
• Add AWS us-gov-west-1 Claude 3.7 Sonnet costs by @nuernber in #15775
• feat(ollama): set 'think' to False when reasoning effort is minimal/none/disable by @kowyo in #15763
• [Feat] Add SENTRY_ENVIRONMENT configuration for Sentry integration by @Thomas-Mildner in #15760
• Add details in docs by @javiergarciapleo in #15721
• [Feat ] /ocr - Add mode + Health check support for OCR models by @ishaan-jaff in #15767
• [Feat] Add def search() APIs for Web Search - Perplexity API by @ishaan-jaff in #15769
• fix(ollama): handle parsing ollama chunk error for issue #13333 by @lshgdut in #15717
• [Feat] Add Tavily Search API by @ishaan-jaff in #15770
• [Feat] Add Parallel AI - Search API by @ishaan-jaff in #15772
• [Feat] Add EXA AI Search API to LiteLLM by @ishaan-jaff in #15774
• feat: Add imageConfig parameter for gemini-2.5-flash-image by @kk-wangjifeng in #15530
• [Feat] Add /search endpoint on LiteLLM Gateway by @ishaan-jaff in #15780
• (feat) Passthrough - set auth on passthrough endpoints, on the UI by @krrishdholakia in #15778
• Fix reasoning item ID auto-generation causing encrypted content verification errors by @Sameerlite in #15782
• Feat: Allow prompt caching to be used for Anthropic Claude on Databricks by @anthonyivn2 in #15801
• fix the date for sonnet 3.7 in govcloud by @nuernber in #15800
• fix: Rename configured_cold_storage_logger to cold_storage_custom_logger by @hula-la in #15798
• fix: Apply max_connections configuration to Redis async client by @hula-la in #15797
• Support for embeddings_by_type Response Format in Bedrock Cohere Embed v1 by @romanglo in #15707
• Fix pass-through endpoint budget enforcement bug by @Sameerlite in #15805

New Contributors

• @talalryz made their first contribution in #15720
• @1vinodsingh1 made their first contribution in #15736
• @Thomas-Mildner made their first contribution in #15760
• @javiergarciapleo made their first contribution in #15721
• @lshgdut made their first contribution in #15717
• @kk-wangjifeng made their first contribution in #15530
• @anthonyivn2 made their first contribution in #15801
• @romanglo made their first contribution in #15707

Full Changelog: v1.78.6-nightly...v1.78.7-nightly