Krish Dholakia
26cd2c4473
Guardrails - add built in guardrails for harmful content, bias, etc. ( #18029 )
...
* feat(litellm_content_filter.py): add support for content filtering categories
make it easy for proxy admin to prevent messages about violence, self harm or illegal weapons going through litellm
* feat: initial commit adding bias detection
allows admin to block inappropriate content about sexual orientation, etc.
* refactor: simplify content_filter.py
use a more exhaustive set of keywords, instead of guessing at potential phrases user can use
* feat(content_filter.py): add new denied topics for in-built content filter guardrails
allow user to automatically block content relating to certain categories from being sent to the LLML
* refactor(content-filter): document new params to litellm content filter
* feat(ui/): litellm content filter - select content categories on ui
* docs: update documentation
* docs(litellm_content_filter.md): document new content filters
2025-12-18 16:28:58 +05:30
Sameer Kankute
d764b7405d
Add thinking to reasoning_effort mapping in v1/messages
2025-12-18 15:29:54 +05:30
YutaSaito
630f3d828e
Merge pull request #18161 from BerriAI/litellm_fix_mcp_list_tool_not_working_without_db
...
Litellm fix mcp list tool not working without db
2025-12-18 18:27:19 +09:00
Leon
1c401ecf71
Add reasoning support for vertex_ai/gemini-3-flash-preview in model prices and context window ( #18175 )
2025-12-18 14:53:36 +05:30
Sameer Kankute
f4f5ea85df
Add redisvl in requirements.txt
2025-12-18 14:42:41 +05:30
Ishaan Jaff
274d996a87
[Feat] New Search API Provider - LinkUp Search ( #18174 )
...
* add linkup search provider
* add Linkup Search docs
* add get_provider_search_config
* get_provider_search_config
* add linkup/search provider
* fix mypy linting
2025-12-18 14:27:36 +05:30
Cesar Garcia
d131b7138d
feat(pricing): add output_cost_per_image_token for gemini-2.5-flash-image models ( #18156 )
...
Add output_cost_per_image_token ($30/1M = 3e-05) to enable correct
image output cost calculation for gemini-2.5-flash-image models.
Affected models:
- gemini-2.5-flash-image
- gemini-2.5-flash-image-preview
- gemini/gemini-2.5-flash-image
- gemini/gemini-2.5-flash-image-preview
- vertex_ai/gemini-2.5-flash-image
2025-12-18 14:08:45 +05:30
Ishaan Jaff
17403967ab
[Bug fix] Vertex Multimodal embeddings - Support text + base64 image combinations ( #18172 )
...
* TestVertexMultimodalEmbedding
* fix _try_merge_text_with_media
* ruff fix
2025-12-18 13:22:43 +05:30
yuneng-jiang
0a4a7408c7
UI Cloudzero delete route
2025-12-17 22:32:39 -08:00
yuneng-jiang
b0d371d864
delete route for cloudzero
2025-12-17 22:12:31 -08:00
yuneng-jiang
c071bfbe58
base commit
2025-12-17 22:05:47 -08:00
yuneng-jiang
8ea7688d35
Adding tests
2025-12-17 21:59:28 -08:00
yuneng-jiang
98c9037ab8
resolve embeddings model config
2025-12-17 21:56:47 -08:00
yuneng-jiang
8ae7d5ce32
base commit
2025-12-17 21:52:51 -08:00
yuneng-jiang
984cbd4529
Merge pull request #18163 from BerriAI/litellm_ui_cloudzero
...
[Feature] UI - Cloud Zero Cost Tracking
2025-12-17 20:24:53 -08:00
Lucas Sugi
9f88d61d10
fix: Change extra_headers to additional_headers ( #17950 )
2025-12-18 08:57:20 +05:30
yuneng-jiang
7b2f33b9b4
Merge pull request #17559 from BerriAI/litellm_new_user_collision_handling
...
[Fix] New user route user_id collision handling
2025-12-17 19:19:41 -08:00
yuneng-jiang
1db7492639
Merge pull request #18159 from BerriAI/litellm_login_500_fix
...
[Fix] Login Page Failed To Parse JSON Error
2025-12-17 19:19:27 -08:00
Sameer Kankute
002532a34f
Merge pull request #18164 from BerriAI/litellm_vertex_gemini_3_model_map
...
Add vertex ai gemini 3 flash in model map
2025-12-18 08:48:55 +05:30
Sameer Kankute
39e16b38c8
Add vertex ai gemini 3 flash in model map
2025-12-18 08:47:02 +05:30
yuneng-jiang
866d1eded5
Merge pull request #17995 from BerriAI/litellm_email_budget_alerts_2
...
[Feature] Email Budget Alerts
2025-12-17 19:16:17 -08:00
yuneng-jiang
37a542293c
Fixing Build
2025-12-17 19:07:29 -08:00
yuneng-jiang
05fb750d7c
UI Cloud Zero Integration
2025-12-17 19:03:39 -08:00
Yuta Saito
80f0a84741
doc: custom_auth object_permission usage for MCP access
2025-12-18 10:25:05 +09:00
Yuta Saito
847bbd4fda
fix: prefer _get_key_object_permission for key lookups and remove redundant checks
2025-12-18 09:50:56 +09:00
yuneng-jiang
dd182a2ed0
Adding tests
2025-12-17 16:28:15 -08:00
yuneng-jiang
b03e73e53b
Add error handling to /v2/login
2025-12-17 16:28:06 -08:00
yuneng-jiang
dcb3a473e6
base commit
2025-12-17 16:27:46 -08:00
yuneng-jiang
f4017a1986
Tests
2025-12-17 16:07:01 -08:00
yuneng-jiang
d7514c0976
Max budget alerts working
2025-12-17 16:01:59 -08:00
yuneng-jiang
19da000bea
revert proxy_config
2025-12-17 15:09:19 -08:00
yuneng-jiang
d6f8e79f0d
bump: version 0.1.26 → 0.1.27
2025-12-17 15:07:16 -08:00
yuneng-jiang
c1e3364c4f
Adding files
2025-12-17 15:05:01 -08:00
yuneng-jiang
dad2a29b2b
Max budget alerts
2025-12-17 15:04:20 -08:00
YutaSaito
6595619906
Merge pull request #18150 from BerriAI/litellm_feat_vault-per-team-config
...
Litellm feat vault per team config
2025-12-18 06:57:24 +09:00
YutaSaito
c694d96da0
Merge pull request #18149 from BerriAI/litellm_feat_add_secret_manager_settings
...
feat: add secret manager settings controls to team management UI
2025-12-18 06:57:12 +09:00
Yuta Saito
1a21965998
fix: ui test
2025-12-18 06:32:50 +09:00
Yuta Saito
b7b22d559e
feat: allow per-team Vault overrides when storing keys
2025-12-18 06:21:53 +09:00
Yuta Saito
b24d6cd47f
feat: add secret manager settings controls to team management UI
2025-12-18 06:09:27 +09:00
Cesar Garcia
f1066a9ad3
docs: expand Responses API section and update endpoints in README ( #17354 )
...
* docs: expand Responses API section and update endpoints in README
- Add full Responses API example with code and output format
- Clarify OpenAI Chat Completions vs Responses API formats
- Update supported endpoints list (completions, responses, embeddings, images, audio, batches)
- Fix consistent output description to be endpoint-agnostic
* update docs
* update README with latest models
2025-12-18 02:30:15 +05:30
Dmitri Tikhonov
844d0d47b7
Fix tag management to preserve encrypted fields in litellm_params ( #17484 )
...
The _add_tag_to_deployment function was directly modifying the
deployment's litellm_params in memory and writing it back to the
database, which caused encrypted API keys and other sensitive fields
to be lost. This fix retrieves the model from the database first,
preserves all existing fields including encrypted ones, adds only the
new tag to the tags array, and updates the database with the modified
params while keeping encrypted fields intact.
Added comprehensive unit tests covering preservation of encrypted
fields, handling of both string and dict litellm_params formats,
duplicate tag prevention, and error handling for missing models.
Generated with [Claude Code](https://claude.com/claude-code )
Co-authored-by: Claude <noreply@anthropic.com>
2025-12-18 02:28:39 +05:30
superpoussin22
1d54c4502d
Add diarize model for openai ( #18117 )
...
* Add pricing and configuration for gpt-4o-transcribe-diarize
* Add GPT-4o transcription pricing and settings
2025-12-18 02:25:42 +05:30
Alexsander Hamir
4134fab74d
add: new security scan ( #18148 )
2025-12-17 12:53:15 -08:00
Ishaan Jaffer
c721c18169
add new docker v
2025-12-18 02:21:36 +05:30
Ishaan Jaff
539f629eff
[Feat] New Logging Integration - Azure Sentinel Logger ( #18146 )
...
* add AzureSentinelLogger
* logging: AzureSentinelLogger
* test_azure_sentinel_signature_and_send_batch
* docs azure sentinel
* fix AzureSentinelLogger
* test fix
* docs fix
* fix: AzureSentinelLogger
* docs sentintel
* feat: add example SLP
* docs sentinel
* docs fix
* docs fix
* docs fix
* fix code qa
* QA fix
* fix test
* TestInitializeInteractionsEndpoints
2025-12-18 02:04:49 +05:30
yuneng-jiang
087dfbf648
Merge remote-tracking branch 'origin' into litellm_email_budget_alerts_2
2025-12-17 11:37:49 -08:00
yuneng-jiang
8cdb481832
Merge remote-tracking branch 'origin' into litellm_new_user_collision_handling
2025-12-17 11:34:46 -08:00
yuneng-jiang
49a1e50672
Merge pull request #17912 from BerriAI/litellm_dd_callback_fix
...
[Fix] Callback Environment Variables Casing
2025-12-17 11:33:41 -08:00
yuneng-jiang
202f71c13a
Merge pull request #17752 from BerriAI/litellm_ui_model_test_connection_fix
...
[Fix] /health/test_connection to resolve env variables like /chat/completions
2025-12-17 11:06:57 -08:00
yuneng-jiang
70f7c8b771
Merge remote-tracking branch 'origin' into litellm_dd_callback_fix
2025-12-17 11:05:46 -08:00
