issues Search Results · repo:BerriAI/litellm language:Python
Filter by
5k results
(67 ms)5k results
inBerriAI/litellm (press backspace or delete to remove)What happened?
I checked the normal operation in config.yml.
- model_name: gemma-3-27b
litellm_params:
model: ISTA-DASLab/gemma-3-27b-it-GPTQ-4b-128g
base_url: http://0.0.0.0:8100/v1
However, ...
bug
hanil-jihun
- 1
- Opened 51 minutes ago
- #11689
What happened?
When using Image edit with Azure OpenAI Service, if We are using API key authentication, We need to set it in the
api-key header. However, the current implementation appears to set the ...
bug
yamada-kazuhiro-tm6
- Opened 5 hours ago
- #11681
The Feature
Ollama now supports thinking with the new think parameter in the ollama.generate and ollama.chat functions. This doesn t
seem to be implemented in LiteLLM yet, however.
Motivation, pitch ...
enhancement
saattrupdan
- Opened 6 hours ago
- #11680
What happened?
Given the following config:
- model_name: google-gemini/*
litellm_params:
model: gemini/*
api_key:
litellm_settings:
check_provider_endpoint: true
Will not ...
bug
matthid
- Opened 9 hours ago
- #11673
The Feature
In the standard logging payload, log a list of StandardLoggingGuardrailInformation for guardrail_information instead of
single instance.
Motivation, pitch
If multiple guardrails are engaged ...
enhancement
thetonus
- Opened 9 hours ago
- #11671
What happened?
As you try to add a vertex model, you are requested to upload the credentials for a GCP SA or use an existing
credential.
You should be allowed to reference a path on the local filesystem ...
bug
mrh-chain
- Opened 9 hours ago
- #11670
What happened?
When adding a new model via the interface, if the provider is Bedrock, then one is required to add a set of AWS
credentials. If LiteLLM is running on an AWS instance with an instance profile ...
bug
mrh-chain
- 1
- Opened 10 hours ago
- #11669
What happened?
For the Gemini Flash 2.5 model (gemini/gemini-2.5-flash-preview-05-20), the cost is listed as this:
output_cost_per_token : 6e-7, output_cost_per_reasoning_token : 0.0000035,
This is not ...
bug
mlops user request
wwwillchen
- Opened 12 hours ago
- #11667
What happened?
Trying to integrate Azure OpenAI into our chat app using a gpt-4.1-mini model.
When i try to call it in my code
litellm._turn_on_debug() result = litellm.completion( model= azure/gpt-4.1-mini ...
bug
mlops user request
leakb
- Opened 12 hours ago
- #11666
What happened?
Reopening with python example.
I try to call different models with tool calls. Working on openai but not on some other ( sonar / claude )
Using : litellm 1.71.1
Is this planned to be ...
bug
simonljn
- Opened 12 hours ago
- #11665

Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.
Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip!
Press the /
key to activate the search input again and adjust your query.