Thomas Rehn
d88771ca49
fix: correct output pricing for gemini-2.5-flash-image-preview https://ai.google.dev/gemini-api/docs/pricing#gemini-2.5-flash-image-preview
2025-09-05 16:22:07 +02:00
Sameer Kankute
231d54741f
Move test to test_litellm/ folder
2025-09-05 10:40:26 +05:30
Sameer Kankute
4fefac1bf2
Move test to test_litellm/ folder
2025-09-05 10:24:55 +05:30
Sameer Kankute
ad9f54a192
Move test to test_litellm/ folder
2025-09-05 10:08:34 +05:30
Sameer Kankute
f7f106f8b8
Move test to test_litellm/ folder
2025-09-05 10:00:58 +05:30
Krish Dholakia
63a2a47ce0
Merge pull request #14003 from BerriAI/teams-on-users-page
...
Team name badge added on the User Details
2025-09-04 21:03:02 -07:00
Krish Dholakia
f67339a86c
Merge pull request #14028 from onlylhf/volcengine-embedding-support
...
Add Volcengine embedding module with handler and transformation logic
2025-09-04 21:01:25 -07:00
Krish Dholakia
62d4623d1c
Merge pull request #14107 from uc4w6c/feat/add_guardrails_anthropic
...
feat: Add guardrail to the Anthropic API endpoint
2025-09-04 20:50:43 -07:00
Krish Dholakia
5d5c19a302
Merge pull request #14077 from TomeHirata/codex/add-support-for-anthropic-citation-api
...
Add support for anthropic citation api in Databricks
2025-09-04 20:46:11 -07:00
Ishaan Jaff
379b0dbf14
[Fix] Ensure team_id is a required field for generating service account keys ( #14270 )
...
* generate_service_account_key_fn
* fix validate_team_id_used_in_service_account_request
* fix types
* test_validate_team_id_used_in_service_account_request_requires_team_id
2025-09-04 18:14:38 -07:00
Ishaan Jaff
5847037b3a
Add validation for STORE_MODEL_IN_DB when updating public model groups ( #14269 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
2025-09-04 14:40:28 -07:00
Ishaan Jaff
1352545617
[Fix] DD LLM Observability - Ensure apm_id is set on traces ( #14272 )
...
* add apm_id for DD LLM
* feat: add _get_apm_trace_id
2025-09-04 14:35:41 -07:00
tobias-mayr
29bbde5257
fix condition ordering and test
2025-09-04 22:18:50 +01:00
Krish Dholakia
94c1b21ae7
Merge branch 'main' into litellm_responses_structured_output
2025-09-04 12:23:26 -07:00
Krish Dholakia
796192dabe
Merge pull request #14130 from moshemorad/bedrock_fix_structure_output
...
Bedrock fix structure output
2025-09-04 12:22:35 -07:00
Krish Dholakia
1c75139cd3
Merge pull request #14136 from BerriAI/add-client-side-pagination
...
Add client side pagination on All Models table
2025-09-04 12:21:48 -07:00
Krish Dholakia
e7b4892124
Merge pull request #14156 from byrongrogan/byron--bedrock-passthrough-override
...
fix: Support AWS_BEDROCK_RUNTIME_ENDPOINT on bedrock passthrough, make work for URLs with a base path
2025-09-04 12:20:17 -07:00
tobias-mayr
d9304b74bd
fix accidental changes
2025-09-04 19:03:25 +01:00
tobias-mayr
2d30b55964
distinguish between gemini models
2025-09-04 18:59:37 +01:00
tobias-mayr
0ade6cceff
remove old code
2025-09-04 18:40:46 +01:00
Sameer Kankute
fc9560573b
[BUG] Fix response api for reasoning item in input for litellm proxy ( #14200 )
...
* fix response api for litellm proxy
* Add test for checking if status is getting removed
* add test in correct file
* remove hardcoded fields
* Make the handling simpler
* fix lint error:
2025-09-04 10:36:48 -07:00
tobias-mayr
99eceb8835
feat: Add support for reasoning_effort='minimal' for Gemini models
...
- Add DEFAULT_REASONING_EFFORT_MINIMAL_THINKING_BUDGET constant (128 tokens)
- Update Gemini transformation to handle 'minimal' reasoning_effort
- Maps 'minimal' to 128 tokens (Gemini's minimum thinking budget)
- Maintains backward compatibility with existing reasoning_effort values
- Fixes issue where Gemini API rejected 0 token thinking budget
2025-09-04 18:29:06 +01:00
Sameer Kankute
8d67392e99
Merge branch 'main' into litellm_responses_structured_output
2025-09-04 22:35:30 +05:30
Sameer Kankute
5f79e8aac6
Litellm passthrough cost tracking chat completion ( #14256 )
...
* feat: add structured output for sdk
* Add support for cost tracking for chat completion in passthrough
* remove not required changes
2025-09-04 09:57:48 -07:00
tanjiro
f82acdfde5
fix z-index
2025-09-05 00:50:55 +09:00
Eitan1112
da136fa07b
Change additionalProperties type to Any
...
This is aligned with "default" which is also `Any`, and both in vertex ai docs:
https://cloud.google.com/vertex-ai/docs/reference/rest/v1/projects.locations.cachedContents#Schema
are both with 'value' type
2025-09-04 18:05:53 +03:00
Ishaan Jaff
1237be04a5
test_aaamodel_prices_and_context_window_json_is_valid
2025-09-04 07:58:20 -07:00
Eitan1112
006ffea98f
Add additionalProperties to vertex ai Schema definition
...
Add additionalProperties field to vertex ai Schema TypedDict
2025-09-04 17:53:40 +03:00
Krish Dholakia
572ac0b88f
Merge pull request #14211 from zhxlp/main
...
fix: image_generation supports extra_body parameter
2025-09-04 07:35:53 -07:00
Krish Dholakia
cb8e3936ae
Merge pull request #14216 from mubashir1osmani/fix_all_docs
...
Fix custom callbacks doc
2025-09-04 07:35:38 -07:00
Krish Dholakia
8738f630ac
Merge pull request #14232 from mubashir1osmani/litellm_docs
...
[docs]: added more info to load balancing & pass through endpoints
2025-09-04 07:31:54 -07:00
Ishaan Jaff
8878951f16
docs fix: disable_add_user_agent_to_request_tags
2025-09-04 07:30:18 -07:00
Krish Dholakia
a8cce5fbf3
Merge pull request #14237 from yeahyung/fix/tpm_limit_bug
...
Fixes #14204 TPM Rate Limit Bug
2025-09-04 07:29:47 -07:00
Krish Dholakia
a74feb221f
Merge pull request #14241 from 22mSqRi/fix-key-reset-and-expires
...
fix: Key Budget not resets at expectable times
2025-09-04 07:29:06 -07:00
22mSqRi
25afa67616
fix: Key Budget not resets at expectable times
2025-09-04 09:04:01 +00:00
yeahyung
7829de2948
( #14204 ) add test code
2025-09-04 16:41:29 +09:00
yeahyung
9e3010daa4
( #14204 ) increase token usage with TTL preservation
2025-09-04 16:41:23 +09:00
mubashir1osmani
b0450d2ddf
docs: added more info to load balancing & passthrough endpoints
2025-09-03 23:58:48 -04:00
Ishaan Jaff
69d5a91e02
bump: version 1.76.2 → 1.76.3
2025-09-03 18:28:52 -07:00
Ishaan Jaff
ab3cd5e96e
fix memory_usage_in_mem_cache cache endpoint vulnerability ( #14229 )
2025-09-03 18:28:11 -07:00
Ishaan Jaff
23ae7170d1
[Feat] Allow using Veo Video Generation through LiteLLM Pass through routes ( #14228 )
...
* fix: add follow_redirects=True,
* test_pass_through_with_httpbin_redirect
* cook book veo video
* docs Veo Video Generation with Google AI Studio
* add veo-3.0-generate-preview cost tracking details
* track vertex_video_models
2025-09-03 18:25:43 -07:00
Ishaan Jaff
be7c762882
add video_generation
2025-09-03 18:25:27 -07:00
Ishaan Jaff
19e2bab8c8
[Feat] Add Initial support for Bedrock Batches API ( #14190 )
...
* fix acreate_file with bedrock
* fix routing to bedrock batches api
* fix create_file
* working batch file upload
* fix batches API for file upload
* test: bedrock files and batches API
* add BaseBatchesConfig
* fix get_provider_batches_config
* transform bedrock batches
* fix run create batch through llm http handler
* test_async_file_and_batch
* main.batches creation
* fix: CommonBatchFilesUtils
* fix async_create_batch
* test_async_file_and_batch
* BedrockBatchesConfig
* fix ruff check
* ruff check fix
* fix docs ref
2025-09-03 17:19:58 -07:00
Ishaan Jaff
beb300abae
[Fix] SCIM - Bug fixes for handling SCIM Group Memberships ( #14226 )
...
* Feat: add better SCIM debugging
* fix _get_scim_member_display
* fix patch_group
* test_update_group_e2e
* test_get_scim_member_value
2025-09-03 16:15:51 -07:00
Ishaan Jaff
e127820bf1
fix proxy_logging_guardrails_model_info_tests
2025-09-03 16:10:30 -07:00
Ishaan Jaff
1d44a6e4a1
Feat: add better SCIM debugging ( #14221 )
2025-09-03 15:52:53 -07:00
Yuta Saito
447016817c
fix: Call guardrail during stream processing
2025-09-04 07:11:44 +09:00
Ishaan Jaff
057d6f5af6
fix: PartnerModelPrefixes
2025-09-03 13:03:04 -07:00
Ishaan Jaff
c9f211f331
fix VertexAIPartnerModels
2025-09-03 13:01:47 -07:00
Ishaan Jaff
8e9352fce7
test fix
2025-09-03 11:06:09 -07:00
