-
-
Notifications
You must be signed in to change notification settings - Fork 3.2k
Insights: BerriAI/litellm
Overview
Could not load contribution data
Please try again later
9 Releases published by 1 person
-
v1.72.1.dev8
published
Jun 6, 2025 -
v1.72.2.dev_image
published
Jun 6, 2025 -
v1.72.0-stable
published
Jun 7, 2025 -
v1.72.2-nightly
published
Jun 7, 2025 -
v1.72.2.rc
published
Jun 8, 2025 -
v1.72.3-nightly
published
Jun 10, 2025 -
v1.72.4-nightly
published
Jun 11, 2025 -
v1.72.5.dev1
published
Jun 11, 2025 -
v1.72.2-stable
published
Jun 12, 2025
93 Pull requests merged by 25 people
-
[Feat] Use dedicated Rest endpoints for list, calling MCP tools
#11684 merged
Jun 13, 2025 -
Revert "Add performance indexes to LiteLLM_SpendLogs for analytics queries"
#11683 merged
Jun 13, 2025 -
Add performance indexes to LiteLLM_SpendLogs for analytics queries
#11675 merged
Jun 13, 2025 -
change space_key header to space_id for Arize
#11595 merged
Jun 13, 2025 -
[Feat] MCP expose streamable https endpoint for LiteLLM Proxy
#11645 merged
Jun 12, 2025 -
Enhance Mistral model support with reasoning capabilities
#11642 merged
Jun 12, 2025 -
[Pricing] add azure/gpt-4o-mini-transcribe models
#11676 merged
Jun 12, 2025 -
Fix default user settings
#11674 merged
Jun 12, 2025 -
fix: Do not add default model on tag based-routing when valid tag
#11454 merged
Jun 12, 2025 -
Correct success message when user creates new budget
#11608 merged
Jun 12, 2025 -
Add wildcard model filter
#11584 merged
Jun 12, 2025 -
Truncate long labels and improve tooltip in Top API Keys chart
#11573 merged
Jun 12, 2025 -
feat(helm): [BerriAI/litellm#11648] support extraContainers in migrations-job.yaml
#11649 merged
Jun 12, 2025 -
Convert scientific notation str to int + Bubble up azure content filter results
#11655 merged
Jun 12, 2025 -
Add bridge for /chat/completion -> /responses API
#11632 merged
Jun 12, 2025 -
Enable System Proxy Support for aiohttp Transport
#11616 merged
Jun 12, 2025 -
Trim the long user ids on the the keys page
#11488 merged
Jun 12, 2025 -
[Feat] Perf fix - ensure deepgram provider uses async httpx calls
#11641 merged
Jun 12, 2025 -
[Feat] MCP - Add support for
streamablehttp_clientMCP Servers#11628 merged
Jun 12, 2025 -
[Feat] Add provider specific params for
deepgram/#11638 merged
Jun 11, 2025 -
[Feat] Add Background mode for Responses API - OpenAI, AzureOpenAI
#11640 merged
Jun 11, 2025 -
[Bug Fix] Add audio/ogg mapping for Audio MIME types
#11635 merged
Jun 11, 2025 -
[UI] Add Deepgram provider to supported providers list and mappings
#11634 merged
Jun 11, 2025 -
fix inference endpoints (#11630)
#11631 merged
Jun 11, 2025 -
Fix Hugging Face Inference Endpoints
#11630 merged
Jun 11, 2025 -
Add Admin-Initiated Password Reset Flow
#11618 merged
Jun 11, 2025 -
Fix: passes api_base, api_key, litellm_params_dict to custom_llm embedding methods
#11450 merged
Jun 11, 2025 -
Add VertexAI Anthropic passthrough - cost calculation, token tracking
#11611 merged
Jun 11, 2025 -
Litellm dev 06 10 2025 p2
#11605 merged
Jun 11, 2025 -
[UI] Polish New MCP Server Add Form
#11604 merged
Jun 11, 2025 -
Add new o3 models pricing
#11606 merged
Jun 10, 2025 -
[Feat] New LLM API Endpoint - Add List input items for Responses API
#11602 merged
Jun 10, 2025 -
[Feat] UI - Add controls for MCP Permission Management
#11598 merged
Jun 10, 2025 -
[Bug Fix] No module named 'diskcache'
#11600 merged
Jun 10, 2025 -
[Feat] LiteLLM Allow setting Uvicorn Keep Alive Timeout
#11594 merged
Jun 10, 2025 -
(fix:exception_mapping_utils.py) fix sglang rate limit error issue
#11575 merged
Jun 10, 2025 -
Enhance chart readability with short-form notation for large numbers
#11571 merged
Jun 10, 2025 -
Add support for new Mistral Magistral models (magistral-medium-2506 and magistral-small-2506)
#11588 merged
Jun 10, 2025 -
Update README.md so docker compose will work as described
#11586 merged
Jun 10, 2025 -
Add "Create New Model" button
#11589 merged
Jun 10, 2025 -
Pangea/kl/udpate readme
#11570 merged
Jun 10, 2025 -
Add VertexAI
claude-opus-4+ Assign users to orgs on creation#11572 merged
Jun 10, 2025 -
Show remaining users on UI + prevent early stream stopping for gemini requests
#11568 merged
Jun 10, 2025 -
Fix gemini tool call indexes
#11558 merged
Jun 10, 2025 -
[Feat] Add Lasso Guardrail to LiteLLM
#11565 merged
Jun 10, 2025 -
Fix: Adds support for choosing the default region based on where the model is available
#11566 merged
Jun 10, 2025 -
Simplify
management_cli.mdCLI docs#10799 merged
Jun 10, 2025 -
Make all commands show server URL
#10801 merged
Jun 10, 2025 -
[Feat] Add
reasoning_effortsupport for perplexity models#11562 merged
Jun 10, 2025 -
[Bug fix]: aiohttp fixes for transfer encoding error on aiohttp transport
#11561 merged
Jun 9, 2025 -
[tests] add mock tests for pplx reasoning
#11564 merged
Jun 9, 2025 -
Update documentation for configuring web search options in config.yaml
#11537 merged
Jun 9, 2025 -
[Docs] Fix incorrect reference to database_url as master_key
#11547 merged
Jun 9, 2025 -
Add gpt-4o-audio-preview-2025-06-03 pricing configuration
#11560 merged
Jun 9, 2025 -
feat: add .cursor to .gitignore
#11538 merged
Jun 8, 2025 -
Update enduser spend and budget reset date based on budget duration
#8460 merged
Jun 8, 2025 -
Ensure consistent 'created' across all chunks + set tool call id for ollama streaming calls
#11528 merged
Jun 8, 2025 -
[Docs] v1.72.2.rc
#11519 merged
Jun 8, 2025 -
UI - fix(add_credentials_tab.tsx): filter for null values when adding credentials
#11525 merged
Jun 7, 2025 -
[Docs] - Add section on using all models with /v1/messages
#11523 merged
Jun 7, 2025 -
Litellm anthropic mcp support
#11474 merged
Jun 7, 2025 -
Audit logs UI improvement
#11446 merged
Jun 7, 2025 -
Simplify experimental multi-instance rate limiter - more accurate
#11424 merged
Jun 7, 2025 -
Update web search documentation for new provider support (xAI, VertexAI, Google AI Studio)
#11515 merged
Jun 7, 2025 -
Fix UI navbar + UI server root path issue + Mask key in audit logs
#11496 merged
Jun 7, 2025 -
Update the correct test directory in contributing_code.md
#11511 merged
Jun 7, 2025 -
Update model version in deploy.md
#11506 merged
Jun 7, 2025 -
Remove retired version gpt-3.5 from configs.md
#11508 merged
Jun 7, 2025 -
Enhance proxy CLI with Rich formatting and improved user experience
#11420 merged
Jun 7, 2025 -
Update production doc
#11499 merged
Jun 6, 2025 -
Fix: Respect user_header_name property for budget selection and user identification
#11419 merged
Jun 6, 2025 -
Update Makefile to match CI workflows and improve contributor experience
#11485 merged
Jun 6, 2025 -
Fix Fireworks AI rate limit exception mapping - detect "rate limit" text in error messages
#11455 merged
Jun 6, 2025 -
Handle file content type transformation in responses api
#11310 merged
Jun 6, 2025 -
Revert "Nebius model pricing info updated"
#11493 merged
Jun 6, 2025 -
Document batch polling logic to avoid ValueError: Output file id is None error
#11286 merged
Jun 6, 2025 -
[Docs] Add audio / tts section for gemini and vertex
#11306 merged
Jun 6, 2025 -
Nebius model pricing info updated
#11445 merged
Jun 6, 2025 -
[Feat] New model - add
codex-mini-latest#11492 merged
Jun 6, 2025 -
Feat: add add azure endpoint for image endpoints
#11482 merged
Jun 6, 2025 -
Add Google Gemini 2.5 Pro Preview 06-05
#11447 merged
Jun 6, 2025 -
Fix variable redefinition linting error in vertex_and_google_ai_studio_gemini.py
#11486 merged
Jun 6, 2025 -
Litellm dev 06 05 2025 p2
#11470 merged
Jun 6, 2025 -
feat: add HuggingFace rerank provider support
#11438 merged
Jun 6, 2025 -
fix: supports_function_calling works with llm_proxy models
#11381 merged
Jun 6, 2025 -
[Fix]: /v1/messages - return streaming usage statistics when using litellm with bedrock models
#11469 merged
Jun 6, 2025 -
[Feat] Return response_id == upstream response ID for VertexAI + Google AI studio (Stream+Non stream)
#11456 merged
Jun 6, 2025
44 Pull requests opened by 27 people
-
[feat] Add CentML as llm provider
#11472 opened
Jun 6, 2025 -
fix: health check failure when mode is set to 'batch'
#11475 opened
Jun 6, 2025 -
[Feat] Prometheus - Allow controlling exposed metrics and labels
#11489 opened
Jun 6, 2025 -
build: test bitnami python
#11497 opened
Jun 6, 2025 -
fix(test_exceptions.py): move exception tests
#11501 opened
Jun 6, 2025 -
Fix issue 9500
#11509 opened
Jun 7, 2025 -
Nebius model pricing info updated
#11514 opened
Jun 7, 2025 -
feat: add structured request model for chat and completion endpoints.
#11516 opened
Jun 7, 2025 -
[Bug Fix] Always include tool calls in output of trim_messages
#11517 opened
Jun 7, 2025 -
Fix Docusaurus package version mismatch error
#11518 opened
Jun 7, 2025 -
Audit logs UI improvement (#11446)
#11522 opened
Jun 7, 2025 -
feat(devcontainer): add database in devcontainer for easier development
#11532 opened
Jun 8, 2025 -
VSCode devcontainer debugging
#11534 opened
Jun 8, 2025 -
Fix wrong cost showing up when using Claude Code
#11536 opened
Jun 8, 2025 -
fix(gemini): filter unsupported schema formats for Gemini API
#11539 opened
Jun 8, 2025 -
Implement GPT-image-1 token-based cost tracking
#11540 opened
Jun 8, 2025 -
[Feature]: Set currency by env variable #8513
#11541 opened
Jun 8, 2025 -
Pass custom_llm_provider_to_embeddings
#11548 opened
Jun 9, 2025 -
fix: handle empty bedrock tool arguments
#11550 opened
Jun 9, 2025 -
Add cache_read_input_token_cost* for gemini
#11554 opened
Jun 9, 2025 -
Add summarize parameter to /spend/logs API for individual transaction logs
#11556 opened
Jun 9, 2025 -
Fixed grok-3-mini to not use stop tokens
#11563 opened
Jun 9, 2025 -
Add bedrock passthrough logging handler for cost tracking etc
#11569 opened
Jun 10, 2025 -
Remove unused ModelDashboard component
#11578 opened
Jun 10, 2025 -
fix(vertex_ai): Handle missing tokenCount in promptTokensDetails
#11581 opened
Jun 10, 2025 -
Add Langfuse OpenTelemetry Integration
#11607 opened
Jun 11, 2025 -
Models Page Improvements
#11619 opened
Jun 11, 2025 -
Usage Charts Improvements
#11620 opened
Jun 11, 2025 -
feat(azure): Make Azure AD scope configurable
#11621 opened
Jun 11, 2025 -
Bugfix/usage for openrouter
#11627 opened
Jun 11, 2025 -
Add "Get Code" Feature
#11629 opened
Jun 11, 2025 -
Adding Palo Alto Networks PRISMA AIRS to Guardrails
#11643 opened
Jun 11, 2025 -
build(deps): bump brace-expansion from 1.1.11 to 1.1.12 in /docs/my-website
#11644 opened
Jun 12, 2025 -
Allow auto-refresh to logs page time selector
#11650 opened
Jun 12, 2025 -
Feat/add delete callback
#11654 opened
Jun 12, 2025 -
fix(ollama): ensure tool calls without parameters are not skipped during streaming
#11658 opened
Jun 12, 2025 -
fix(vertex_ai): support global location in vertex ai passthrough
#11661 opened
Jun 12, 2025 -
Fix speech-to-text fallbacks
#11663 opened
Jun 12, 2025 -
Add missing api_key and api_base.
#11668 opened
Jun 12, 2025 -
Add LiteLLM_HealthCheckTable to database schema
#11677 opened
Jun 12, 2025 -
Implement health check backend API and storage functionality
#11678 opened
Jun 12, 2025 -
Implement health check frontend UI components and dashboard integration
#11679 opened
Jun 12, 2025 -
[Feat] Add Authentication + Permission Management for MCP List, Call Tool Ops
#11682 opened
Jun 13, 2025 -
Chat Completions <-> Responses API Bridge Improvements
#11685 opened
Jun 13, 2025
94 Issues closed by 17 people
-
[Feature]: Proxy - Support passing through OpenAI, anthropic API Keys from request headers
#3332 closed
Jun 13, 2025 -
Gpt-4o-audio enhancements
#6385 closed
Jun 13, 2025 -
[Bug]: Infinite loop when checking `get_openai_supported_params`
#7185 closed
Jun 13, 2025 -
[Bug]: Admin UI Redirects Endlessly with SSO Login
#9027 closed
Jun 13, 2025 -
[Bug]: Got exception from REDIS Connection closed by server
#9024 closed
Jun 13, 2025 -
[Feature]: ChatLiteLLMRouter to support json_schema
#9043 closed
Jun 13, 2025 -
[Bug]: cached tokens are not priced when using custom handler
#9049 closed
Jun 13, 2025 -
[Feature]: make function calling work with azure openai o3-mini
#9053 closed
Jun 13, 2025 -
[Feature]: Upgrade to the MCP streamable http transport
#11603 closed
Jun 12, 2025 -
[Bug]: Not able to get annotations from gpt4o-search-preview
#11491 closed
Jun 12, 2025 -
[Bug]: Tag Based Routing redirecting to default model
#6770 closed
Jun 12, 2025 -
[Bug]: Budget UI - Should show Budget Created
#9347 closed
Jun 12, 2025 -
[Feature]: enable prompt caching by default in model configuration for bedrock claude models
#9805 closed
Jun 12, 2025 -
ImportError: cannot import name 'CompletionTokensDetails' from 'openai.types.completion_usage'
#11664 closed
Jun 12, 2025 -
[Bug]: Anthropic model calls with Tools : Input should be a valid dictionary
#11196 closed
Jun 12, 2025 -
[Bug]: Add Bedrock Support for /v1/messages API
#9159 closed
Jun 12, 2025 -
[Bug]: POST /key/generate requires Enterprise
#11552 closed
Jun 12, 2025 -
[Feature]: support extra containers in migrations-job.yaml helm template
#11648 closed
Jun 12, 2025 -
[Bug]: LiteLLM Proxy $0 Cost Tracking for Codestral
#11266 closed
Jun 12, 2025 -
[Question] Is codex-mini-latest (responses-API only models) supported?
#10925 closed
Jun 12, 2025 -
Add support for using Responses API in /chat/completions spec
#9754 closed
Jun 12, 2025 -
[Bug]: Proxy Server env HTTP__PROXY is not taking effect
#11389 closed
Jun 12, 2025 -
Forcing Structured JSON Output in LiteLLM + OpenRouter (FIXED)
#11653 closed
Jun 12, 2025 -
[Bug]: Sonnet 3.7 got capped at 64k instead of 128k
#8984 closed
Jun 12, 2025 -
[Bug]: Documented custom SSO handler raises an exception
#9030 closed
Jun 12, 2025 -
[Bug]: Unable to find token in cache or `LiteLLM_VerificationTokenTable`
#11639 closed
Jun 11, 2025 -
[Bug]: disk cache fails on docker image
#11637 closed
Jun 11, 2025 -
[Feature]: Background mode in the Responses API
#11308 closed
Jun 11, 2025 -
[Bug]: team models not visible to an internal user
#11633 closed
Jun 11, 2025 -
[Bug]: UI not accessible
#11592 closed
Jun 11, 2025 -
[Feature]: add o3-pro
#11597 closed
Jun 11, 2025 -
[Bug]: MCP not functional as expected
#11617 closed
Jun 11, 2025 -
[Bug]: Why Nova-pro-v1(bedrock) generates reasoning block?
#10932 closed
Jun 11, 2025 -
Star the Repository
#11625 closed
Jun 11, 2025 -
[Bug]: Swagger and Ui issue with kubernetes
#10626 closed
Jun 11, 2025 -
[Bug]: incorrect completion_start_time for streaming request
#8999 closed
Jun 11, 2025 -
OpenMeter Integration: "Error at \"/subject\": value must be a string
#9006 closed
Jun 11, 2025 -
[Feature]: OpenAI Responses API Support
#9146 closed
Jun 10, 2025 -
[Bug]: `No module named 'diskcache'`
#11503 closed
Jun 10, 2025 -
pinokio
#11576 closed
Jun 10, 2025 -
[Bug]: context_window_fallbacks not triggered when using sglang due to unmapped error message
#10793 closed
Jun 10, 2025 -
[Bug]: Missing ID in tool_calls under stream mode
#11407 closed
Jun 10, 2025 -
[Bug]: Vertex AI gemini-2.5-pro-preview returns an empty string response in v1.72.2
#11549 closed
Jun 10, 2025 -
using openrouter, why is grok3 or gemini 2.5 not available in the drop-down?
#11567 closed
Jun 10, 2025 -
[Feature]: reasoning_effort for Perplexity api
#11543 closed
Jun 10, 2025 -
[Feature]: add litellm embedding to langchain
#1437 closed
Jun 10, 2025 -
[Feature]: Support Computer Control from Anthropic claude-3-5-sonnet-20240620
#6391 closed
Jun 10, 2025 -
[Feature]: UI openRouter Models
#6635 closed
Jun 10, 2025 -
[Bug]: VertexAI custom model does not pick up uploaded token
#8597 closed
Jun 10, 2025 -
[Bug]: Memory Leak in `completion()` with `stream=True`
#8620 closed
Jun 10, 2025 -
[Feature]: Add ENFER.AI LLM Provider
#8968 closed
Jun 10, 2025 -
[Feature]: Support litellm.base_url
#8981 closed
Jun 10, 2025 -
[Feature]: MCP Crud DB Operations
#11010 closed
Jun 9, 2025 -
[Bug]: /ui is not accessible
#11531 closed
Jun 9, 2025 -
[Bug]: custom_llm_provider deepseek - unhealthy health status / invalid base_url
#8146 closed
Jun 9, 2025 -
[Bug]: Can't stream Deepseek on Vertex AI Model Garden
#8564 closed
Jun 9, 2025 -
[Bug]: Vertex AI - files stored in GCS without file extension are not processed
#8809 closed
Jun 9, 2025 -
[Feature]: Can base_url be set instead of using the official base_url when calling the model
#8952 closed
Jun 9, 2025 -
[Feature]: Use timstamp with timezone in LLM Proxy DB schema instead
#8955 closed
Jun 9, 2025 -
Erro in Vertex AI call with Streamming and async mode
#8960 closed
Jun 9, 2025 -
[Bug]: end-user budget_duration stills not seem to reset
#7129 closed
Jun 8, 2025 -
[Bug]: ollama_chat streaming tool calls cannot be reconstructed, due to missing tool call id from ollama
#11262 closed
Jun 8, 2025 -
[Bug]: stream response from /v1/chat/completions should return same created param
#11437 closed
Jun 8, 2025 -
[Bug]: Watsonx.ai does not allow space ID using the 'deployment/' endpoint
#10941 closed
Jun 8, 2025 -
[Bug]: UI Page Logo Missing
#11473 closed
Jun 8, 2025 -
[Bug]: Error encountered with LiteLLM – Debug mode not resolving issue
#8938 closed
Jun 8, 2025 -
Add "R7" in "model_prices_and_context_window.json"
#8941 closed
Jun 8, 2025 -
[Bug]: The contributing code document shows outdated test directory
#11510 closed
Jun 7, 2025 -
[Bug]: litellm.APIConnectionError: 'str' object has no attribute 'get'
#11442 closed
Jun 7, 2025 -
[Bug]: Deployment documentation uses the outdated model GPT-3.5
#11505 closed
Jun 7, 2025 -
[Bug]: valid tokens do not longer work after 1.52.14
#7287 closed
Jun 7, 2025 -
[Bug]: Default values in json responses issue
#8351 closed
Jun 7, 2025 -
[Bug]: KeyError: 'name' error with local ollama models
#8594 closed
Jun 7, 2025 -
Increased around 40ms ASR Latency at P50 After Integrating with LiteLLM
#8671 closed
Jun 7, 2025 -
Facing this Error "litellm.NotFoundError: VertexAIException" while using "gemini-pro" model
#8824 closed
Jun 7, 2025 -
[Bug]: Task was destroyed but it is pending! with new litellme version
#8831 closed
Jun 7, 2025 -
LiteLLM.Info: If you need to debug this error, use `litellm.set_verbose=True'.
#8906 closed
Jun 7, 2025 -
[Bug]: Deepseek-r1's reasoning content is missing in latest version v1.61.20.rc
#8909 closed
Jun 7, 2025 -
[Bug]: _transform_responses_api_content_to_chat_completion_content` doesn't support file content type
#11309 closed
Jun 6, 2025 -
Add "openai/codex-mini" in "model_prices_and_context_window.json"
#11176 closed
Jun 6, 2025 -
Problème avec OpenRouter AI
#11416 closed
Jun 6, 2025 -
[Bug]: /images/edits reports an error on azure gpt-image-1
#11429 closed
Jun 6, 2025 -
[Bug]: Mismatch in uvicorn dependency on conda-forge
#11328 closed
Jun 6, 2025 -
[Bug]: bedrock does not support parameters: ['tools'], for model=us.meta.llama4-scout-17b-instruct-v1:0
#11430 closed
Jun 6, 2025 -
[Bug]: `input_type` not supported on proxy for azure_ai cohere-embed-v-4
#11434 closed
Jun 6, 2025 -
[Bug]:
#11441 closed
Jun 6, 2025 -
[Feature]: Add Huggingface Text Embeddings Inference (TEI) provider for `/rerank`
#8372 closed
Jun 6, 2025
55 Issues opened by 54 people
-
[Bug]: When using Image edit with Azure OpenAI Service, the API key is set in the Authorization header.
#11681 opened
Jun 13, 2025 -
[Feature]: Support `think` parameter for Ollama models
#11680 opened
Jun 12, 2025 -
[Bug]: Model-Discovery not working when using a different frontend-name
#11673 opened
Jun 12, 2025 -
[Feature]: Support logging for multiple guardrails
#11671 opened
Jun 12, 2025 -
[Bug]: Adding a Vertex model doesn't allow referencing credentials in the environment
#11670 opened
Jun 12, 2025 -
[Bug]: Unable to create bedrock model without credentials
#11669 opened
Jun 12, 2025 -
[Bug]: Gemini Flash 2.5 cost calculation is incorrect
#11667 opened
Jun 12, 2025 -
[Bug]: no attribute 'choices' when calling Azure OpenAI via SDK
#11666 opened
Jun 12, 2025 -
[Bug]: Errors with perplexity and anthropic calls with Tools
#11665 opened
Jun 12, 2025 -
[Bug]: "Resource not found" occurred when call /images/edits with azure/gpt-image-1
#11660 opened
Jun 12, 2025 -
[Bug]: aiohttp "Unclosed client session" warning when using Ollama embeddings
#11657 opened
Jun 12, 2025 -
[Bug]: Unknown Premium error
#11656 opened
Jun 12, 2025 -
[Feature]:
#11651 opened
Jun 12, 2025 -
[Bug]: Budget reset for users does not work through the UI where default budgets are present
#11636 opened
Jun 11, 2025 -
[Bug]: Openrouter streaming Doesn't Return 'cost' and 'is_byok' from openrouter
#11626 opened
Jun 11, 2025 -
[Bug]: Allow separate timeout setting for connection handshaking failures (Azure OpenAI, APIConnectionError)
#11624 opened
Jun 11, 2025 -
[Bug]: errors when using database and config models
#11623 opened
Jun 11, 2025 -
[Bug]: impossible to update budget on teams
#11613 opened
Jun 11, 2025 -
[BUG] LLM Provider NOT provided error when using fully local model
#11596 opened
Jun 10, 2025 -
[Bug]: Huggingface dedicated inference endpoints no longer works
#11593 opened
Jun 10, 2025 -
[Bug]: SSL verification issues with Azure AI client starting from litellm 1.69
#11591 opened
Jun 10, 2025 -
[Feature]: Add a close method to LangFuseLogger class
#11590 opened
Jun 10, 2025 -
[Bug]: Unable to pass image in request to Mistral models via Async Client
#11587 opened
Jun 10, 2025 -
[Bug]: Vertex AI pass-through not working with global location
#11585 opened
Jun 10, 2025 -
[Bug]: tool_calls index starts from 1
#11580 opened
Jun 10, 2025 -
[Bug]: person invited to the team does not belong to the team's organization
#11579 opened
Jun 10, 2025 -
Improve docs for add_function_to_prompt flag
#11577 opened
Jun 10, 2025 -
[Bug]: Caching completely broken with cache_control parameter when using PromptCachingDeploymentCheck
#11574 opened
Jun 10, 2025 -
[Bug]: MLFlow autologging not working (cannot schedule new futures after interpreter shutdown.)
#11559 opened
Jun 9, 2025 -
[Bug]: gemini-2.5-pro doesn't take reasoning parameter error
#11557 opened
Jun 9, 2025 -
[Bug]: SCIM provisioning not adding members to team
#11555 opened
Jun 9, 2025 -
[Bug]: Litellm virtual key generation
#11551 opened
Jun 9, 2025 -
[Bug]: Anthropic messages provider config not found for model
#11544 opened
Jun 9, 2025 -
[Bug]: Upgrade boto3
#11542 opened
Jun 8, 2025 -
[Bug]:
#11535 opened
Jun 8, 2025 -
[Feature]: POE.com API proxy
#11530 opened
Jun 8, 2025 -
[Bug]: Gemini - Invalid content part type: file
#11529 opened
Jun 8, 2025 -
[Bug]: Amazon Bedrock Agents Usage always zero (litellm SDK)
#11526 opened
Jun 7, 2025 -
[Bug]: Getting litellm.supports_reasoning == False, even for supported models.
#11520 opened
Jun 7, 2025 -
[Bug]: Config document uses the outdated model gpt-3.5
#11507 opened
Jun 7, 2025 -
[Bug]: Langfuse custom logger initialization error
#11500 opened
Jun 6, 2025 -
[Bug]: not able to use async_redis.SSLConnection with Redis >=6.0.0
#11498 opened
Jun 6, 2025 -
[Bug]: Incorrect cost calculation for Gemini models with tiered token pricing
#11495 opened
Jun 6, 2025 -
Add " openrouter Deepseek R1 0528 Qwen3 8B" in "model_prices_and_context_window.json"
#11490 opened
Jun 6, 2025 -
[Bug]: FileNotFoundError for custom_callbacks.py when deploying via Helm (works with Docker)
#11487 opened
Jun 6, 2025 -
[Bug]: uvicorn dependency version too low
#11484 opened
Jun 6, 2025 -
[Bug]: ollama_chat "keep_alive" isn't working
#11483 opened
Jun 6, 2025 -
[Bug]: Admin Panel - blank page
#11481 opened
Jun 6, 2025 -
[Bug]: In-memory Prompt Injection Detection not working despite being activated in config
#11480 opened
Jun 6, 2025 -
[Feature]: Support for Tool Calling with Amazon SageMaker AI
#11479 opened
Jun 6, 2025 -
[Bug]: Support Mistral OCR from Azure AI foundry
#11478 opened
Jun 6, 2025 -
[Bug]: Configuring Pass-Through Endpoints through the UI interface leads to memory leaks.
#11477 opened
Jun 6, 2025 -
[Bug]: Much longer running time Vision Anthropic model compared to anthropic SDK
#11476 opened
Jun 6, 2025 -
[Bug]: Getting an error using Claude-Sonnet-4 (thinking mode) via Google Vertex AI
#11471 opened
Jun 6, 2025
129 Unresolved conversations
Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.
-
feat: add redis ssl and username support
#11319 commented on
Jun 6, 2025 • 1 new comment -
[Feature]: Add support for Mistral Codestral through Azure
#8679 commented on
Jun 12, 2025 • 0 new comments -
[Feature]: Add Multi-Modal Output Support (image-to-image, image-to-video, text-to-video)
#8548 commented on
Jun 12, 2025 • 0 new comments -
[Feature]: Time To First Token Timeout
#5859 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: Groq's distil-whisper-large-v3-en not working with litellm_stable_release_branch-v1.72.0.rc
#11325 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: Response Format should be supported for OpenRouter
#10465 commented on
Jun 12, 2025 • 0 new comments -
[Feature]: Support Gemini imagen
#11087 commented on
Jun 12, 2025 • 0 new comments -
[Feature]: LiteLLM Java client SDK
#11276 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: Azure gpt-image-1 cost tracking not working when size/quality set to auto or left default
#10335 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: Adding a selfhosted TGI endpoint to config.yaml makes LiteLLM stuck on pod startup
#10937 commented on
Jun 12, 2025 • 0 new comments -
JSON Parse Error in Streaming Handler
#10410 commented on
Jun 12, 2025 • 0 new comments -
gemini 2.5 pro Error parsing chunk
#9564 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: metadata.api_base metric no longer emitted by otel after v1.49.0
#10389 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: azure_ai foundry models not working
#11227 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: OpenRouter models missing from LiteLLM
#9858 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: LiteLLM Team Table expanding makes /v1/models slow
#10849 commented on
Jun 12, 2025 • 0 new comments -
Azure OpenAI call using the AZURE_API_BASE URL with suffix.
#9266 commented on
Jun 13, 2025 • 0 new comments -
[feature] support `/v1/completions` on aiohttp_openai/ route
#9099 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: Disable regenerate key option when user is a premium user
#9195 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: How to add response id and reasoning_content with CustomLLM?
#9197 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: create_pretrained_tokenizer uses wrong parameter name auth_token for Tokenizer.from_pretrained call
#9199 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: UI - Max Budget on Usage page always displays No limit
#9205 commented on
Jun 12, 2025 • 0 new comments -
Add "chatgpt" in "model_prices_and_context_window.json"
#9207 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: o3-mini via Azure does not support Structured Outputs
#9212 commented on
Jun 12, 2025 • 0 new comments -
[Bug]: Bedrock Cohere Embeddings Error
#9213 commented on
Jun 12, 2025 • 0 new comments -
🎅 I WISH LITELLM HAD...
#361 commented on
Jun 11, 2025 • 0 new comments -
[Feature]: Improving Retry Mechanism Consistency and Logging for Streamed Responses in LiteLLM Proxy
#8648 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: logs blowing up with `Cannot add callback - would exceed MAX_CALLBACKS limit of 30.`
#9792 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: Wrong Gemini 2.5 cost calculation
#11156 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: Prisma Migrate fails with a custom install
#10024 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: Documentation error - Incorrect AWS environment variable names
#9794 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: ssl_verify=false has no effect anymore
#9340 commented on
Jun 11, 2025 • 0 new comments -
Use HTTP or SOCKS proxy
#10453 commented on
Jun 6, 2025 • 0 new comments -
[Feat] Add Qdrant Vector Store to supported Vector Stores
#11468 commented on
Jun 9, 2025 • 0 new comments -
Pricing backup
#11439 commented on
Jun 6, 2025 • 0 new comments -
Better handling of Sagemaker models
#11410 commented on
Jun 7, 2025 • 0 new comments -
Improve streaming error handling: Clean logs and consistent retry behavior
#11406 commented on
Jun 6, 2025 • 0 new comments -
Update Clarifai Provider Documentation with Latest Models and OpenAI-Compatible Interface
#11397 commented on
Jun 9, 2025 • 0 new comments -
Added the Create new model button acknowledging the changes requested
#11255 commented on
Jun 7, 2025 • 0 new comments -
fix: enhance AzureOpenAIResponsesAPIConfig to support different Azure…
#11027 commented on
Jun 9, 2025 • 0 new comments -
feat: add a health_check_voice parameter in model_info
#10940 commented on
Jun 11, 2025 • 0 new comments -
Improve test coverage of models CLI command
#10931 commented on
Jun 10, 2025 • 0 new comments -
fix issue with parsing assistant messages
#10917 commented on
Jun 12, 2025 • 0 new comments -
Add sorting to `models list` command
#10630 commented on
Jun 10, 2025 • 0 new comments -
fix(litellm/caching/caching_handler.py): fix kwargs[litellm_params][p…
#10612 commented on
Jun 10, 2025 • 0 new comments -
Add support for SageMaker Inference Components in sagemaker chat
#10603 commented on
Jun 11, 2025 • 0 new comments -
handle check_provider_endpoint:True with multiple wildcard models via openai like provider
#10358 commented on
Jun 9, 2025 • 0 new comments -
fix: Fix passing scope id for watsonx inferencing
#10012 commented on
Jun 6, 2025 • 0 new comments -
fix bedrock embedding invocations with app inference profiles
#9902 commented on
Jun 11, 2025 • 0 new comments -
test: comment out flaky azure tests
#9230 commented on
Jun 13, 2025 • 0 new comments -
Draft
#9181 commented on
Jun 11, 2025 • 0 new comments -
fix(router.py): use a copy of item in model list - prevent item in di…
#9088 commented on
Jun 8, 2025 • 0 new comments -
(Feat) - Raise BadRequestError when calling native /v1/messages with unsupported provider/model
#9087 commented on
Jun 8, 2025 • 0 new comments -
Litellm dev 03 05 2025 contributor prs
#9079 commented on
Jun 8, 2025 • 0 new comments -
1215同步
#7243 commented on
Jun 11, 2025 • 0 new comments -
Integrating Not Diamond with LiteLLM
#4971 commented on
Jun 11, 2025 • 0 new comments -
add function call response parser for non openai models
#768 commented on
Jun 7, 2025 • 0 new comments -
[Bug]: Valid config keys have changed in V2
#7560 commented on
Jun 13, 2025 • 0 new comments -
[Bug]: litellm slower then python's request
#7764 commented on
Jun 13, 2025 • 0 new comments -
[Feature]: Add apac.amazon.nova-* Model Support
#9228 commented on
Jun 13, 2025 • 0 new comments -
why won't any huggingface text2image models work?
#9236 commented on
Jun 13, 2025 • 0 new comments -
LiteLLM cannot handle image responses from TogetherAI's text2image model Stabeldiffusion due to an additional 'ID' field being sent from togetherAI in the response
#9239 commented on
Jun 13, 2025 • 0 new comments -
[Feature]: Allow API Keys to be loaded from files, not just environment variables or directly in the config.yaml
#9240 commented on
Jun 13, 2025 • 0 new comments -
[Bug]: Missing documentation on tags used for containers
#9256 commented on
Jun 13, 2025 • 0 new comments -
[Bug]: LiteLLM Cache: Excepton add_cache: sequence item 1: expected str instance, list found
#9265 commented on
Jun 13, 2025 • 0 new comments -
[Feature]: Set currency by env variable
#8513 commented on
Jun 8, 2025 • 0 new comments -
[Bug]: enable_preview_features=True leaks metadata to provider on OpenAI-compatible endpoints (can be security issue too)
#9104 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: `provider_specific_fields` not set when using `stream_chunk_builder`
#9103 commented on
Jun 9, 2025 • 0 new comments -
[Feature]: Support for Huggingface models and other Sagemaker Jumpstart Models
#9090 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: multi instance virtual key tpm rpm setting can not synchronization
#9008 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: Fireworks tool call ids being concatenated from every chunk
#8990 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: Mistral stream completion request error with litellm proxy server
#8978 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: `index` field not populated for a chunk with `choices` when calling tools using OpenAI (streaming mode, n>1)
#8977 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: BadRequestError when passing a GCS URI to Gemini models
#8849 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: Inconsistent VertexAI calls due to intermittent auth issues
#8771 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: Embeddings request fails on /v1/embeddings
#8744 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: Model info API with whisper and Dall-e
#7584 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: migration job only runs if there is a change in values
#7536 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: default value for DATABASE_URL not being set in 1.17.1
#11191 commented on
Jun 9, 2025 • 0 new comments -
[Feature]: Spend Logs API Filter should maintain same response schema when date range filters are given
#11449 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: Error parsing chunk: Expecting property name enclosed in double quotes
#5650 commented on
Jun 9, 2025 • 0 new comments -
[Bug]: together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct not correctly parsing tool response
#11453 commented on
Jun 6, 2025 • 0 new comments -
[Bug] [litellm proxy]: Gemini second requests never works until proxy is restarted
#11322 commented on
Jun 6, 2025 • 0 new comments -
[Bug]: litellm fails to block requests over end-user budget when user header used
#11083 commented on
Jun 6, 2025 • 0 new comments -
[Bug]: The current mcp tool list interface is too slow
#11436 commented on
Jun 6, 2025 • 0 new comments -
Add Azure Responses API support
#9653 commented on
Jun 6, 2025 • 0 new comments -
[Feature]: Support Vertex AI dedicated endpoints
#10436 commented on
Jun 6, 2025 • 0 new comments -
Error 400 when using pydantic objects with default options defined with Google models.
#7808 commented on
Jun 7, 2025 • 0 new comments -
[Bug]: The term 'litellm' is not recognized as the name of a cmdlet, function, script file, or operable program.
#3163 commented on
Jun 7, 2025 • 0 new comments -
[Bug]: IndexError: list index out of range in Azure GPT Calls
#9500 commented on
Jun 7, 2025 • 0 new comments -
[Bug]: Request truncated in spend logs
#10988 commented on
Jun 7, 2025 • 0 new comments -
[Bug]: All requests getting timed out and not reaching Anthropic
#11345 commented on
Jun 7, 2025 • 0 new comments -
[Bug]: Unable to link LiteLLM with Cline
#9784 commented on
Jun 7, 2025 • 0 new comments -
[Feature]: Support FetchAI provider and asi-1-mini model
#9092 commented on
Jun 8, 2025 • 0 new comments -
[Bug]: Model analytics page showing model retry settings
#9045 commented on
Jun 8, 2025 • 0 new comments -
[Feature]: Create Ruby SDK
#7109 commented on
Jun 8, 2025 • 0 new comments -
[Bug]: Wrong cost for Anthropic models, cached tokens cost not being correctly considered.
#11364 commented on
Jun 8, 2025 • 0 new comments -
[Bug]: o4-mini models fails to add in dashboard
#10204 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: max_token is ignored when invoking a Fireworks AI model from the LiteLLM Proxy Server
#11002 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: Failed to export traces to otlp.arize.com: StatusCode.UNKNOWN - "space_key is required"
#11465 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: gemini/gemma-3-27b-it function calling is not enabled exception
#10313 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: litellm fails to process title request from librechat
#9857 commented on
Jun 10, 2025 • 0 new comments -
Duplicate entries in model_prices_and_context_window.json
#9158 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: Router's completion() method does not work with a redis cache for caching cooldown, only the asynchronous acompletion() method works
#9156 commented on
Jun 11, 2025 • 0 new comments -
[Feature]: Support FanoutCache
#9153 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: LiteLLM.Info: If you need to debug this error, use `litellm._turn_on_debug()'.
#9136 commented on
Jun 11, 2025 • 0 new comments -
[info]: Regarding models compatible with OpenAI-Compatible Endpoints, such as Qwen. etc
#7471 commented on
Jun 11, 2025 • 0 new comments -
[Feature]: Support Qdrant vector store
#11365 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: groq/whisper-large-v3 returns 400 BadRequestError with OPENAI_TRANSCRIPTION_PARAMS
#11402 commented on
Jun 11, 2025 • 0 new comments -
Notice: Deprecation of the Prisma Python client
#9753 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: Model Not Mapped Yet - Unable to Use
#8536 commented on
Jun 11, 2025 • 0 new comments -
[Feature]: Make Azure AD scope a configurable parameter in get_azure_ad_token_from_entrata_id
#9847 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: embedding over proxy for an OpenAI-compatible endpoint not working
#11231 commented on
Jun 11, 2025 • 0 new comments -
[Bug]: Async task pending error on adding fallback models to completion
#10517 commented on
Jun 9, 2025 • 0 new comments -
[Feature]: Dark Mode
#10177 commented on
Jun 9, 2025 • 0 new comments -
Error Running the Program
#9142 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: System message is not being logged in Helicone when using Bedrock
#9141 commented on
Jun 10, 2025 • 0 new comments -
Cannot connect to huggingface embedding
#9137 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: Remove token validation in LiteLLM client
#9132 commented on
Jun 10, 2025 • 0 new comments -
embedding model connection error
#9125 commented on
Jun 10, 2025 • 0 new comments -
litellm.exceptions.APIConnectionError: litellm.APIConnectionError: OllamaException -
#9121 commented on
Jun 10, 2025 • 0 new comments -
[Feature]: reset budget according to calender month
#9098 commented on
Jun 10, 2025 • 0 new comments -
[Feature]: `litellm.supports_reasoning` and `drop_params` working with reasoning
#8765 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: Floating point rounding errors in x-litellm-response-cost header
#8867 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: Transitive dependency on tenacity not understood by bazel
#8704 commented on
Jun 10, 2025 • 0 new comments -
Ollama Server error '502 Bad Gateway'
#8510 commented on
Jun 10, 2025 • 0 new comments -
[Bug]: AWS Sagemaker embedding calls are failing with a Jina endpoint
#11019 commented on
Jun 10, 2025 • 0 new comments -
[Feature]: Support reranker with vllm provider
#11415 commented on
Jun 10, 2025 • 0 new comments -
Regression: Redis/Valkey cache backend not initializing, `/cache/ping` endpoint 404, no cache health in Docker (v1.71.x+)
#11243 commented on
Jun 10, 2025 • 0 new comments