4fdeff8e1a
Fix token_counter with special token input
2025-08-07 22:58:07 +08:00
dfada882f1
vtx test fix gemini-2.5-flash-lite
2025-08-07 00:11:10 -07:00
9c5e9d7362
add groq/openai/gpt-oss ( #13363 )
2025-08-07 00:08:18 -07:00
043c12b11e
added token breakdown in ui ( #13357 )
2025-08-06 19:03:58 -07:00
b7325f4765
[MCP Gateway] Added route check for internal users ( #13350 )
...
* added route check
* fix ruff
2025-08-06 15:32:21 -07:00
c3cc10387e
added new migration files ( #13345 )
2025-08-06 13:12:39 -07:00
a92bf8173e
Fix create, search vector store error ( #13285 )
...
* (#13284 ) add avector_store_create to route_type which doesn't require model
* (#13284 ) exclude hidden params in metadata when create vector store
* (#13284 ) fix lint error
* (#13284 ) keep metadata None if metadata is None(not empty dict)
* (#13284 ) add test code
* (#13284 ) change test code name
* (#13284 ) add avector_store_search to route_type which doesn't require model
2025-08-06 11:15:17 -07:00
b1a8968895
[MCP Gateway] fix auth on ui for bearer servers ( #13312 )
...
* fix auth on ui for bearer servers
* add tests and fixes
* fix tests
2025-08-06 09:46:10 -07:00
28a894cb06
[Feat] - New model - Add Bedrock gpt oss models - "openai.gpt-oss-20b-1:0", "openai.gpt-oss-120b-1:0" ( #13342 )
...
* add openai.gpt-oss-20b-1:0
* update BEDROCK_CONVERSE_MODELS
* openai.gpt-oss-20b-1:0 fixes
* fix PDF input
2025-08-06 09:24:04 -07:00
eeed03a78f
test fix: gcp deprecated gemini-1.5-flash
2025-08-06 08:43:45 -07:00
596592599a
feat: Add logo customization for LiteLLM admin UI ( #12958 )
...
* feat: Add logo customization for LiteLLM admin UI
- Add simple logo customization page under Settings > UI Theme
- Support custom logo URL with instant preview
- Clean reset to default functionality
- Wrap app with ThemeProvider for proper context
- Backend properly handles null/empty logo URLs
* style: Update save button to use indigo color and 'Save Changes' text for consistency
* fix: Restore CloudZero background job initialization
Address PR review feedback by restoring the _initialize_spend_tracking_background_jobs method
that handles both CloudZero and Prometheus background job initialization. This ensures
critical spend tracking functionality is not lost while preserving the logo customization feature.
Changes:
- Restore _initialize_spend_tracking_background_jobs method
- Replace inline Prometheus initialization with proper method call
- Maintain CloudZero background job setup for cost tracking
2025-08-06 08:10:08 -07:00
f74d9f1963
fix(pyproject.toml): fix version
2025-08-05 22:03:47 -07:00
0da25fadc0
Exclude none fields on /chat/completion - fixes n8n bug + Allow calling /v1/models when end user over budget ( #13320 )
...
* fix(proxy_server.py): exclude none fields before returning
Fixes https://github.com/BerriAI/litellm/issues/13055
* test: add unit tests
* feat(auth_checks.py): allow info routes to work when end user over budget
Fixes https://github.com/BerriAI/litellm/issues/13286
2025-08-05 21:39:46 -07:00
92c525ddfe
feat(JinaAI): support multimodal embedding models ( #13181 )
...
* feat(JinaAI): support multimodal embedding models
* add test case
* add test
* fix test
2025-08-05 19:21:56 -07:00
324cfe8bdc
fix(streaming_handler.py): include cost in streaming usage object ( #13319 )
...
Fixes https://github.com/BerriAI/litellm/issues/12689
2025-08-05 18:38:31 -07:00
2e3f564a39
fix: fix map
2025-08-05 18:33:36 -07:00
50c4a32c7d
docs claude-opus-4-1-20250805
2025-08-05 18:02:22 -07:00
4c1adeaf67
bump: version 1.75.1 → 1.75.2
2025-08-05 17:53:15 -07:00
352b7ae913
build(model_prices_and_context_window.json): add vertex ai claude-opus-4.1
...
Add claude opus 4.1
2025-08-05 17:52:35 -07:00
da40b5ec47
bump litellm enterprise
2025-08-05 17:50:40 -07:00
0308a835b8
bump: version 0.1.17 → 0.1.18
2025-08-05 17:47:16 -07:00
b6fcda2f8a
[LLM Translation] Fix model group on clientside auth with API calls ( #13314 )
...
* fix unsupported operand type(s) for +=: 'NoneType' and 'str' on clientside auth creds for responses
* fix the client side auth to use correct metadata
* add more tests
* fix tests
2025-08-05 17:46:47 -07:00
b455ada161
[Bug Fix] [Bug]: New Databricks Foundation Models databricks-gpt-oss-20b and databricks-gpt-oss-120b failed with error: litellm.APIConnectionError: 'signature' ( #13318 )
...
* test_transform_choices_without_signature
* fix ChatCompletionThinkingBlock
* extract_reasoning_content
2025-08-05 17:46:40 -07:00
dab8ba03e3
[Feat] - When using custom tags on prometheus allow using wildcard patterns ( #13316 )
...
* _tag_matches_wildcard_configured_pattern
* test_get_custom_labels_from_tags_wildcard_patterns
* docs Custom Tags
* docs how custom tags work
* fix
2025-08-05 17:46:13 -07:00
0ccc493455
[Bug]: Fix Mimetype Resolution Error in Bedrock Document Understanding ( #13309 )
...
* fix _validate_format for BedrockImageProcessor
* add test
* fix _validate_format for bedrock
* _get_document_format
* test_bedrock_get_document_format_fallback_mimes
* fix: add fallback method for mime type detection
2025-08-05 17:07:10 -07:00
b2146713e5
refactor mcp guardrails ( #13238 )
2025-08-05 16:26:36 -07:00
2399fd49ab
fix for baseurl ending with / ( #13289 )
2025-08-05 16:14:59 -07:00
8b2478e7d6
[Proxy server] Add apscheduler log suppress ( #13299 )
...
* Add log suppress
* Add log suppress
2025-08-05 15:04:51 -07:00
7524aa386c
[Redis IAM] Change documentation ( #13306 )
...
* change docs
* addde note
2025-08-05 15:04:46 -07:00
475aa06117
anthropic.claude-opus-4
2025-08-05 14:08:21 -07:00
32501c85f5
fix unsupported operand type(s) for +=: 'NoneType' and 'str' on clientside auth creds for responses ( #13293 )
2025-08-05 13:16:16 -07:00
fd92f3eaf1
team req for service acc ( #13302 )
2025-08-05 13:01:54 -07:00
2eef77d960
add fireworks gpt-oss-20b ( #13303 )
2025-08-05 12:30:09 -07:00
0db13acdc7
New models - add fireworks_ai/glm-4p5 model family ( #13297 )
...
* add fireworks_ai/glm-4p5
* fix max output tokens
2025-08-05 12:08:42 -07:00
cc5c7aba03
[New model] add bedrock/us.anthropic.claude-opus-4-1-20250805-v1:0 ( #13295 )
...
* add us.anthropic.claude-opus-4-1-20250805-v1:0 bedrock model
* fix BEDROCK_CONVERSE_MODELS
2025-08-05 11:56:47 -07:00
1b9dd9daee
claude opus 4.1 support for anthropic provider ( #13296 )
2025-08-05 11:56:10 -07:00
609fa9f5ca
[LLM Translation + Coding tools] Added litellm claude code count tokens support ( #13261 )
...
* Added litellm claude code count tokens support
* fix mypy
* create helper
* Revert construct
* revert construct
* fix return
* Add reutrn none
* change to factory approach
* refactor to BaseModelInfo
* enum fix
2025-08-05 10:57:24 -07:00
29a8c583c2
added redis iam auth ( #13275 )
2025-08-05 10:56:34 -07:00
7c42659a98
Revert "Fix: Langfuse reporting "client closed" error due to httpx client TTL…" ( #13291 )
...
This reverts commit 1c6be9bdad
2025-08-05 09:58:57 -07:00
5a02eb473b
test_function_calling_with_tool_response
2025-08-05 09:55:47 -07:00
416da066eb
fix(main.py): handle tool being a pydantic object ( #13274 )
...
* fix(main.py): handle tool being a pydantic object
Fixes https://github.com/BerriAI/litellm/issues/13064
* fix(prompt_templates/common_utils.py): fix unpack defs deepcopy issue
Fixes https://github.com/BerriAI/litellm/issues/13151
* fix(utils.py): handle tools is none
2025-08-04 23:44:02 -07:00
eb49f987de
Ensure disable_llm_api_endpoints works + Add wildcard model support for 'team-byok' model ( #13278 )
...
* fix(route_checks.py): ensure disable llm api endpoints is correctly set
* fix(route_checks.py): raise httpexception
raise expected exceptions
* fix(router.py): handle team only wildcard models
fixes issue where team only wildcard models were not considered during auth checks
* fix(router.py): handle team only wildcard models
fixes issue where team only wildcard models were not considered during auth checks
2025-08-04 23:19:51 -07:00
af67c3576f
fix OCI linting errors ( #13279 )
...
* fix(types/llms/oci.py): fix linting errors
* fix(oci.py): fix linting error
* fix(oci.py): fix linting errors
* fix: fix linting error
* fix: fix linting error
2025-08-04 23:10:46 -07:00
ec205fec35
[UI] - Add ability to set model alias per key/team ( #13276 )
...
* update model alias on keys
* team model aliases
* fix model aliases
* fixes for teams
2025-08-04 21:47:39 -07:00
efd34966dc
[LLM Translation] Support /v1/models/{model_id} retrieval ( #13268 )
...
* added model id endpoint
* fix test
* add route to internal users
* make the functions reusable
* fixed mypy
2025-08-04 18:03:59 -07:00
de7108b5f8
input cost per token higher than 1 test ( #13270 )
2025-08-04 18:02:03 -07:00
ad26cba8b6
add litellm-enterprise==0.1.17
2025-08-04 17:26:50 -07:00
8314227a60
bump: version 1.75.0 → 1.75.1
2025-08-04 17:24:40 -07:00
d948b47dba
bump: version 1.74.15 → 1.75.0
2025-08-04 17:23:55 -07:00
ba1882fdd5
[Bug Fix] Prometheus - fix for litellm_input_tokens_metric, litellm_output_tokens_metric - Note this updates the metric name ( #13271 )
...
* fixes for litellm_tokens_metric
* test_prometheus_token_metrics_with_prometheus_config
2025-08-04 17:22:21 -07:00
Yikai Zhao