scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-08 03:08:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 115
26088 commits 3285 branches 1443 tags 4.8 GiB
Commit graph

26088 commits

This branch
This branch
All branches
Author SHA1 Message Date
Ishaan Jaffer
ce7499c8f7 fix sec tests 2025-09-26 19:06:10 -07:00
Ishaan Jaffer
55849706f9 fix local_testing 2025-09-26 18:59:11 -07:00
Ishaan Jaffer
0769ac2fdd bump litellm-proxy-extras/0.2.21 2025-09-26 18:49:41 -07:00
Ishaan Jaffer
dd0744b746 fix mypy 2025-09-26 18:46:09 -07:00
Krrish Dholakia
1c939c70e5 feat(discoverable_endpoints.py): use encryption + encoding to securely handle state + redirect uri without storing in db 
would needlessly flood the db
 2025-09-26 18:39:10 -07:00
Ishaan Jaffer
9bed9995f8 bump pip install "mypy==1.18.2 2025-09-26 18:32:42 -07:00
Ishaan Jaffer
bbbf204fe8 ui linting fix 2025-09-26 18:22:44 -07:00
Ishaan Jaffer
81765bba17 fix fastuuid 2025-09-26 18:20:32 -07:00
Ishaan Jaff
36cc98254c
[Fix] Parallel Request Limiter v3 - ensure Lua scripts can execute on redis cluster (#14968) 
* use hashtag slots for rate limiting logic

* redis_startup_nodes fix

* test_execute_redis_batch_rate_limiter_script_cluster_compatibility

* async_increment_tokens_with_ttl_preservation
 2025-09-26 18:15:57 -07:00
Krrish Dholakia
0d36e6cbe9 fix(discoverable_endpoints.py): redirect to redirect uri 2025-09-26 18:13:12 -07:00
Alexsander Hamir
bcc7fe74db
fix: support documented params (#14969) 2025-09-26 17:39:09 -07:00
Krrish Dholakia
667df3c3db fix: revert commit 2025-09-26 17:21:42 -07:00
Ishaan Jaff
628cd13755
[Feat] UI - Allow scheduling key rotations when creating virtual keys (#14960) 
* fix design of key reset interval

* fix: LiteLLM_VerificationToken

* fix key manager

* add key_rotation_at

* ui fix

* fix ui view

* set key_rotation_at  on creation

* add key_rotation_at

* fix info

* fix: _set_key_rotation_fields

* fix KeyRotationManager

* fix key edit view

* test_update_key_fn_auto_rotate_enable

* fix KeyRotationManager
 2025-09-26 16:24:40 -07:00
Maximgitman
f2d7c1c14d Fix Anthropic streaming IDs 2025-09-26 18:31:10 -04:00
Krrish Dholakia
342e80d48d feat: initial commit for v2 oauth flow 2025-09-26 15:25:42 -07:00
Sameer Kankute
076cb4654e
fix mypy errors from bitbucket integration (#14959) 2025-09-26 14:08:17 -07:00
Ishaan Jaffer
56b3258c40 Revert "fix design of key reset interval" 
This reverts commit 75146f04428b45796ee4e7dab83ef958f77daee6.
 2025-09-26 13:38:38 -07:00
Ishaan Jaffer
3ea45ec03a fix design of key reset interval 2025-09-26 13:38:38 -07:00
Sameerlite
ce0b815959 fix test 2025-09-27 02:08:09 +05:30
Mubashir Osmani
b039374c71
Azure Managed Batches - api key error (#14932) 
* added qwen models and gpt-5-codex

* fix flaky test

* fix failing test

* Added retries to prisma client state

* fix: prisma client state retries in pods

* Revert "fix failing test"

This reverts commit dbec4988a2.

* Revert "fix flaky test"

This reverts commit b0ac2f2dc3.

* Revert "added qwen models and gpt-5-codex"

This reverts commit 9a8a8f2d47.

* Revert "fix: prisma client state retries in pods"

This reverts commit 04e58e5ca1.

* fix lint

* Revert "fix lint"

This reverts commit 5303d52a5e.

* fixed lint

* fix: azure api key managed batch files
 2025-09-26 13:35:35 -07:00
Sameerlite
92cb34eb25 fix mypy errors 2025-09-27 02:02:24 +05:30
Alexsander Hamir
2973ff8be9
fix: remove slow string operation (#14955) 
* fix: remove slow string operation

* fix: behavior change

* fix: behavior change

* fix: avoid default call
 2025-09-26 13:25:59 -07:00
Sameer Kankute
94edbd1b35
Merge pull request #14957 from BerriAI/main 
merge main
 2025-09-27 01:54:44 +05:30
Sameer Kankute
3dac7e28fc
Potential fix for code scanning alert no. 3413: Clear-text logging of sensitive information 
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
 2025-09-27 01:18:34 +05:30
Sameerlite
61a450f2e2 fix lint 2025-09-27 01:16:09 +05:30
Sameerlite
66cf281331 fix lint 2025-09-27 01:03:21 +05:30
Sameerlite
67e7ad5aa9 Add vertex live api passthrough with cost tracking 2025-09-27 00:55:47 +05:30
Ishaan Jaffer
35930d7ccb fix key rotation settings 2025-09-26 12:21:57 -07:00
Ishaan Jaffer
1009a38ff4 Add key expiry and auto-rotation settings 
- Create KeyLifecycleSettings component grouping expiry and auto-rotation
- Add dedicated 'Key Expiry & Auto-Rotation' accordion section
- Fix auto-rotation toggle visibility with proper layout
- Move expire key field from Optional Settings to new section
- Remove old AutoRotationSettings component
- Integrate auto-rotation metadata in form submission
 2025-09-26 12:02:14 -07:00
Ishaan Jaffer
e2e2ae78a4 test fix 2025-09-26 11:48:28 -07:00
Ishaan Jaffer
4a75d042fb fix test 2025-09-26 11:45:52 -07:00
Ishaan Jaff
ea8d0bb7d5 fix: re-add scheduled rotations 2025-09-26 11:40:46 -07:00
Nicolas Herment
50f625433d
Revert incorrect changes to sonnet-4 max output tokens (#14933) 2025-09-26 11:19:52 -07:00
Ishaan Jaffer
539d10f9cb test fix 2025-09-26 11:06:26 -07:00
Ishaan Jaff
d04c6d4eea
[Feat] Add new anthropic web fetch tool support (#14951) 
* add web_fetch tool for ANTHROPIC_HOSTED_TOOLS

* add ANTHROPIC_BETA_HEADER_VALUES, ANTHROPIC_HOSTED_TOOLS

* feat: add web fetch tool anthropic

* test_anthropic_tool_use

* docs web fetch

* docs fix

* docs fix
 2025-09-26 11:04:11 -07:00
Olivier Cornelis
6fe8c33448
docs: add documentation for additional cost-related keys in custom pricing (#14949) 
Co-authored-by: aider (openrouter/anthropic/claude-sonnet-4) <aider@aider.chat>
 2025-09-26 10:32:30 -07:00
Ishaan Jaff
360befa216
[Feat] Add support for Gemini 2.5 Flash and Flash-lite preview models (09-2025 release) (#14948) 
* add gemini-2.5-flash-preview-09-2025

* docs add gemini-2.5-flash-preview-09-2025 model family
 2025-09-26 09:51:38 -07:00
Alex Shoop
914844122c
Fix: revert fastuuid optional dependency, always use fastuuid in .__uid helper (#14941) 
* always use fastuuid

* rm from proxy extras since its now default

* poetry lock
 2025-09-26 09:14:20 -07:00
Daniel Klein
de795a4531 Fix inconsistent token configs for gpt-5 models 2025-09-26 09:43:26 -04:00
Toy-97
6c95bd926f
update: DeepInfra model data refresh [2025-09-26] 
Added models:
deepinfra/deepseek-ai/DeepSeek-V3.1-Terminus

Removed models:
deepinfra/zai-org/GLM-4.5-Air

Modified models:
deepinfra/NousResearch/Hermes-3-Llama-3.1-70B:
   - input_cost_per_token: 1.2e-07 → 3e-07

deepinfra/Qwen/Qwen3-32B:
   - output_cost_per_token: 3e-07 → 2.8e-07

deepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct:
   - max_tokens: 4096 → 262144
   - max_output_tokens: 4096 → 262144
   - max_input_tokens: 4096 → 262144

deepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking:
   - max_tokens: 4096 → 262144
   - max_output_tokens: 4096 → 262144
   - max_input_tokens: 4096 → 262144

deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507:
   - input_cost_per_token: 1.3e-07 → 9e-08

deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct:
   - input_cost_per_token: 2.3e-07 → 4e-07

deepinfra/google/gemini-2.5-flash:
   - output_cost_per_token: 1.75e-06 → 2.5e-06
   - input_cost_per_token: 2.1e-07 → 3e-07

deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo:
   - output_cost_per_token: 2e-08 → 3e-08
   - input_cost_per_token: 1.5e-08 → 2e-08

deepinfra/meta-llama/Llama-3.2-3B-Instruct:
   - output_cost_per_token: 2.4e-08 → 2e-08
   - input_cost_per_token: 1.2e-08 → 2e-08

deepinfra/Sao10K/L3-8B-Lunaris-v1-Turbo:
   - input_cost_per_token: 2e-08 → 4e-08

deepinfra/openai/gpt-oss-120b:
   - input_cost_per_token: 9e-08 → 5e-08

deepinfra/google/gemini-2.5-pro:
   - output_cost_per_token: 7e-06 → 1e-05
   - input_cost_per_token: 8.75e-07 → 1.25e-06

deepinfra/NousResearch/Hermes-3-Llama-3.1-405B:
   - output_cost_per_token: 8e-07 → 1e-06
   - input_cost_per_token: 7e-07 → 1e-06

deepinfra/Qwen/Qwen3-235B-A22B:
   - output_cost_per_token: 6e-07 → 5.4e-07
   - input_cost_per_token: 1.3e-07 → 1.8e-07

deepinfra/nvidia/Llama-3.1-Nemotron-70B-Instruct:
   - output_cost_per_token: 3e-07 → 6e-07
   - input_cost_per_token: 1.2e-07 → 6e-07

deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo:
   - output_cost_per_token: 1.2e-07 → 3.9e-07
   - input_cost_per_token: 3.8e-08 → 1.3e-07

deepinfra/deepseek-ai/DeepSeek-V3-0324:
   - input_cost_per_token: 2.8e-07 → 2.5e-07
   - cache_read_input_token_cost: 2.24e-07 → None

deepinfra/mistralai/Mistral-Small-3.2-24B-Instruct-2506:
   - output_cost_per_token: 1e-07 → 2e-07
   - input_cost_per_token: 5e-08 → 7.5e-08

deepinfra/Qwen/Qwen3-235B-A22B-Thinking-2507:
   - output_cost_per_token: 6e-07 → 2.9e-06
   - input_cost_per_token: 1.3e-07 → 3e-07

deepinfra/zai-org/GLM-4.5:
   - output_cost_per_token: 2e-06 → 1.6e-06
   - input_cost_per_token: 5.5e-07 → 4e-07

deepinfra/mistralai/Mixtral-8x7B-Instruct-v0.1:
   - output_cost_per_token: 2.4e-07 → 4e-07
   - input_cost_per_token: 8e-08 → 4e-07

deepinfra/openai/gpt-oss-20b:
   - output_cost_per_token: 1.6e-07 → 1.5e-07

deepinfra/google/gemma-3-27b-it:
   - output_cost_per_token: 1.7e-07 → 1.6e-07
 2025-09-26 20:11:26 +08:00
Matéo Evan Muller
b12fa388ad
Fix vLLM provider rerank endpoint from /v1/rerank to /rerank 2025-09-26 13:13:17 +02:00
Krish Dholakia
2f3155c2ee
Merge pull request #14858 from oytunkutrup1/litellm_fix_gpt3.5_price_fix 
GPT-3.5-Turbo price updated.
 2025-09-25 23:47:43 -07:00
Krish Dholakia
6a1be4722e
Merge pull request #14879 from huangyafei/update_price 
Add gpt-5 and gpt-5-codex to OpenRouter cost map
 2025-09-25 23:46:35 -07:00
Krish Dholakia
79ebb2c95e
Merge pull request #14888 from mrFranklin/feat/improve-opik 
feat: improve opik integration code
 2025-09-25 23:40:41 -07:00
Krish Dholakia
f2f75bf911
Merge pull request #14893 from vertexcover-io/fix/openai-image-edit-support-images 
🐛 Fix a bug where openai image edit siltently ignores multiple images
 2025-09-25 23:37:52 -07:00
Ritesh Kadmawala
af0cb7c277 🐛 Fix a bug where openai image edit siltently ignores multiple images 2025-09-26 10:56:06 +05:30
Mubashir Osmani
625ed3f8cf
fix: prisma client state retries (#14925) 
* added qwen models and gpt-5-codex

* fix flaky test

* fix failing test

* Added retries to prisma client state

* fix: prisma client state retries in pods

* Revert "fix failing test"

This reverts commit dbec4988a2.

* Revert "fix flaky test"

This reverts commit b0ac2f2dc3.

* Revert "added qwen models and gpt-5-codex"

This reverts commit 9a8a8f2d47.

* Revert "fix: prisma client state retries in pods"

This reverts commit 04e58e5ca1.

* fix lint

* Revert "fix lint"

This reverts commit 5303d52a5e.

* fixed lint
 2025-09-25 21:54:00 -07:00
Vishnu Patibandla
fb9e2c93a0
add noma guardrail provider to ui (#14415) 
* add noma guardrail provider to ui

* resolved linting issues

* fix return value
 2025-09-25 21:53:15 -07:00
Teddy Amkie
0e8f60fe67
Remove aiohttp_ prefix from config (#14920) 
* Fix: Correct model name in load test advanced docs

Co-authored-by: teddy <teddy@berri.ai>

* Fix: Update load testing provider to openai/fake

Co-authored-by: teddy <teddy@berri.ai>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-09-25 16:09:41 -07:00
Ishaan Jaffer
dcfe6dd3d9 linting fix 2025-09-25 16:07:02 -07:00