config.yaml

#This default config file aims to support most popular model providers out of the box

#In general, the model name used by the client will be the same as the ones from the provider (For example, you will use "anthropic.claude-3-5-sonnet-20240620-v1:0" when you're calling LiteLLM just like you would when calling Amazon Bedrock directly)
#In the case where there are model name conflicts, a prefix will be used (For example, the Azure and the openAI model names conflict, so when you are using Azure, you will use "azure/gpt-4o-realtime-preview-2024-10-01")

#Some model providers require additional user-specific configuration (such as Azure which requires you to specify your own api_base with your resource name, and your api_version). 
#In this case, the provider is commented out, and you should uncomment it and provide your specific info

#For more detailed information about each provider, refer to the docs: https://docs.litellm.ai/docs/providers

#If you are not interested in a particular provider, just remove it from your config.yaml, and redeploy, and it will no longer show up in your LiteLLM deployment

#If a particular provider is not working, double check your .env file, and make sure you have provided a valid api key for that provider, and then redeploy

model_list:
  #Bedrock Models
  - model_name: anthropic.claude-3-5-sonnet-20240620-v1:0
    litellm_params:
      model: bedrock/anthropic.claude-3-5-sonnet-20240620-v1:0
  # - model_name: anthropic.claude-3-5-sonnet-20240620-v1:0
  #   litellm_params:
  #     model: bedrock/meta.llama3-70b-instruct-v1:0
  - model_name: anthropic.claude-3-sonnet-20240229-v1:0
    litellm_params:
      model: bedrock/anthropic.claude-3-sonnet-20240229-v1:0
  - model_name: anthropic.claude-3-haiku-20240307-v1:0
    litellm_params:
      model: bedrock/anthropic.claude-3-haiku-20240307-v1:0
      guardrailConfig: {"guardrailIdentifier": "6wcr934j0wgu", # The identifier (ID) for the guardrail.
        "guardrailVersion": "1", # The version of the guardrail.
}
  - model_name: anthropic.claude-3-opus-20240229-v1:0
    litellm_params:
      model: bedrock/anthropic.claude-3-opus-20240229-v1:0
  - model_name: meta.llama3-1-405b-instruct-v1:0
    litellm_params:
      model: bedrock/meta.llama3-1-405b-instruct-v1:0
  - model_name: meta.llama3-1-70b-instruct-v1:0
    litellm_params:
      model: bedrock/meta.llama3-1-70b-instruct-v1:0
  - model_name: meta.llama3-1-8b-instruct-v1:0
    litellm_params:
      model: bedrock/meta.llama3-1-8b-instruct-v1:0
  - model_name: meta.llama3-70b-instruct-v1:0
    litellm_params:
      model: bedrock/meta.llama3-70b-instruct-v1:0
  - model_name: meta.llama3-8b-instruct-v1:0
    litellm_params:
      model: bedrock/meta.llama3-8b-instruct-v1:0
  - model_name: amazon.titan-embed-text-v2:0
    litellm_params:
      model: bedrock/amazon.titan-embed-text-v2:0
  - model_name: amazon.titan-embed-text-v1
    litellm_params:
      model: bedrock/amazon.titan-embed-text-v1
  - model_name: amazon.titan-embed-image-v1
    litellm_params:
      model: bedrock/amazon.titan-embed-image-v1
  - model_name: cohere.embed-english-v3
    litellm_params:
      model: bedrock/cohere.embed-english-v3
  - model_name: cohere.embed-multilingual-v3
    litellm_params:
      model: bedrock/cohere.embed-multilingual-v3
  #OpenAI Models
  - model_name: gpt-4o-realtime-preview-2024-10-01
    litellm_params:
      model: openai/gpt-4o-realtime-preview-2024-10-01
  - model_name: o1-mini
    litellm_params:
      model: openai/o1-mini
  - model_name: o1-preview
    litellm_params:
      model: openai/o1-preview
  - model_name: gpt-4o-mini
    litellm_params:
      model: openai/gpt-4o-mini
      #tpm: 10000 #Set tokens per minute. Will stop sending traffic to this model once exceeded, and will send traffic to fallback models if configured.
      #rpm: 1 #Set requests per minute. Will stop sending traffic to this model once exceeded, and will send traffic to fallback models if configured.
  - model_name: gpt-4o-mini-2024-07-18
    litellm_params:
      model: openai/gpt-4o-mini-2024-07-18
  - model_name: gpt-4o
    litellm_params:
      model: openai/gpt-4o
  - model_name: gpt-4o-2024-08-06
    litellm_params:
      model: openai/gpt-4o-2024-08-06
  - model_name: gpt-4o-2024-05-13
    litellm_params:
      model: openai/gpt-4o-2024-05-13
  - model_name: gpt-4-turbo
    litellm_params:
      model: openai/gpt-4-turbo
  - model_name: gpt-4-0125-preview
    litellm_params:
      model: openai/gpt-4-0125-preview
  - model_name: gpt-4-1106-preview
    litellm_params:
      model: openai/gpt-4-1106-preview
  - model_name: gpt-3.5-turbo
    litellm_params:
      model: openai/gpt-3.5-turbo
  - model_name: gpt-3.5-turbo-1106
    litellm_params:
      model: openai/gpt-3.5-turbo-1106
  - model_name: gpt-3.5-turbo-0301
    litellm_params:
      model: openai/gpt-3.5-turbo-0301
  - model_name: gpt-3.5-turbo-0613
    litellm_params:
      model: openai/gpt-3.5-turbo-0613
  - model_name: gpt-3.5-turbo-16k
    litellm_params:
      model: openai/gpt-3.5-turbo-16k
  - model_name: gpt-3.5-turbo-16k-0613
    litellm_params:
      model: openai/gpt-3.5-turbo-16k-0613
  - model_name: gpt-4
    litellm_params:
      model: openai/gpt-4
  - model_name: gpt-4-0314
    litellm_params:
      model: openai/gpt-4-0314
  - model_name: gpt-4-0613
    litellm_params:
      model: openai/gpt-4-0613
  - model_name: gpt-4-32k
    litellm_params:
      model: openai/gpt-4-32k
  - model_name: gpt-4-32k-0314
    litellm_params:
      model: openai/gpt-4-32k-0314
  - model_name: gpt-4-32k-0613
    litellm_params:
      model: openai/gpt-4-32k-0613
  - model_name: gpt-4-vision-preview
    litellm_params:
      model: openai/gpt-4-vision-preview
  - model_name: text-embedding-3-small
    litellm_params:
      model: openai/text-embedding-3-small
  - model_name: text-embedding-3-large
    litellm_params:
      model: openai/text-embedding-3-large
  - model_name: text-embedding-ada-002
    litellm_params:
      model: openai/text-embedding-ada-002
  #Gemini Models
  - model_name: gemini-1.5-flash
    litellm_params:
      model: gemini/gemini-1.5-flash
  - model_name: gemini-1.5-flash-8b
    litellm_params:
      model: gemini/gemini-1.5-flash-8b
  - model_name: gemini-1.5-pro
    litellm_params:
      model: gemini/gemini-1.5-pro
  #Anthropic Models
  - model_name: claude-3-5-sonnet-20240620
    litellm_params:
      model: anthropic/claude-3-5-sonnet-20240620
  - model_name: claude-3-haiku-20240307
    litellm_params:
      model: anthropic/claude-3-haiku-20240307
  - model_name: claude-3-opus-20240229
    litellm_params:
      model: anthropic/claude-3-opus-20240229
  - model_name: claude-3-5-sonnet-20240620
    litellm_params:
      model: anthropic/claude-3-5-sonnet-20240620
  - model_name: claude-3-sonnet-20240229
    litellm_params:
      model: anthropic/claude-3-sonnet-20240229
  #Mistral Models
  - model_name: mistral-small-latest
    litellm_params:
      model: mistral/mistral-small-latest
  - model_name: mistral-medium-latest
    litellm_params:
      model: mistral/mistral-medium-latest
  - model_name: mistral-large-2407
    litellm_params:
      model: mistral/mistral-large-2407
  - model_name: mistral-large-latest
    litellm_params:
      model: mistral/mistral-large-latest
  - model_name: open-mistral-7b
    litellm_params:
      model: mistral/open-mistral-7b
  - model_name: open-mixtral-8x7b
    litellm_params:
      model: mistral/open-mixtral-8x7b
  - model_name: open-mixtral-8x22b
    litellm_params:
      model: mistral/open-mixtral-8x22b
  - model_name: codestral-latest
    litellm_params:
      model: mistral/codestral-latest
  - model_name: open-mistral-nemo
    litellm_params:
      model: mistral/open-mistral-nemo
  - model_name: open-mistral-nemo-2407
    litellm_params:
      model: mistral/open-mistral-nemo-2407
  - model_name: open-codestral-mamba
    litellm_params:
      model: mistral/open-codestral-mamba
  - model_name: codestral-mamba-latest
    litellm_params:
      model: mistral/codestral-mamba-latest
  #Codestral API Models
  - model_name: text-completion-codestral/codestral-latest
    litellm_params:
      model: text-completion-codestral/codestral-latest
  - model_name: text-completion-codestral/codestral-2405
    litellm_params:
      model: text-completion-codestral/codestral-2405
  #Cohere Models
  - model_name: command-r-plus-08-2024
    litellm_params:
      model: cohere/command-r-plus-08-2024
  - model_name: command-r-08-2024
    litellm_params:
      model: cohere/command-r-08-2024
  - model_name: command-r-plus
    litellm_params:
      model: cohere/command-r-plus
  - model_name: command-r
    litellm_params:
      model: cohere/command-r
  - model_name: command-light
    litellm_params:
      model: cohere/command-light
  - model_name: command-nightly
    litellm_params:
      model: cohere/command-nightly
  #Huggingface Models 
  #(Follow the below pattern to support any Huggingface serverless model you want to use from this list: https://huggingface.co/models?inference=warm&pipeline_tag=text-generation) 
  #(For custom models, text classification models, or dedicated inference endpoints, refer to the docs: https://docs.litellm.ai/docs/providers/huggingface)
  - model_name: meta-llama/Llama-3.2-1B
    litellm_params:
      model: huggingface/meta-llama/Llama-3.2-1B
  - model_name: meta-llama/Llama-3.2-3B-Instruct
    litellm_params:
      model: huggingface/meta-llama/Llama-3.2-3B-Instruct
  - model_name: meta-llama/Llama-3.2-1B-Instruct
    litellm_params:
      model: huggingface/meta-llama/Llama-3.2-1B-Instruct
  - model_name: meta-llama/Llama-3.2-3B
    litellm_params:
      model: huggingface/meta-llama/Llama-3.2-3B
  - model_name: meta-llama/Llama-3.1-70B-Instruct
    litellm_params:
      model: huggingface/meta-llama/Llama-3.1-70B-Instruct
  - model_name: mistralai/Mixtral-8x7B-Instruct-v0.1
    litellm_params:
      model: huggingface/mistralai/Mixtral-8x7B-Instruct-v0.1
  - model_name: mistralai/Mistral-7B-v0.1
    litellm_params:
      model: huggingface/mistralai/Mistral-7B-v0.1
  - model_name: mistralai/Mistral-7B-Instruct-v0.3
    litellm_params:
      model: huggingface/mistralai/Mistral-7B-Instruct-v0.3
  - model_name: codellama/CodeLlama-7b-hf
    litellm_params:
      model: huggingface/codellama/CodeLlama-7b-hf
  - model_name: bigcode/starcoder2-15b
    litellm_params:
      model: huggingface/bigcode/starcoder2-15b
  #Nvidia NIM models (Supports all Nvidia nim models following the same pattern as below) 
  #More config examples here: https://docs.litellm.ai/docs/providers/nvidia_nim 
  #Full list of models here: https://docs.api.nvidia.com/nim/reference/models-1
  - model_name: nvidia/nemotron-4-340b-reward
    litellm_params:
      model: nvidia_nim/nvidia/nemotron-4-340b-reward
  - model_name: nvidia/nemotron-4-340b-instruct
    litellm_params:
      model: nvidia_nim/nvidia/nemotron-4-340b-instruct
  - model_name: meta/llama3-70b
    litellm_params:
      model: nvidia_nim/meta/llama3-70b
  #XAI Models
  - model_name: grok-beta
    litellm_params:
      model: xai/grok-beta
  - model_name: grok-vision-beta
    litellm_params:
      model: xai/grok-vision-beta
  #Perplexity AI Models
  - model_name: "pplx-7b-chat"
    litellm_params:
      model: "perplexity/pplx-7b-chat"
  - model_name: "pplx-70b-chat"
    litellm_params:
      model: "perplexity/pplx-70b-chat"
  - model_name: "pplx-7b-online"
    litellm_params:
      model: "perplexity/pplx-7b-online"
  - model_name: "pplx-70b-online"
    litellm_params:
      model: "perplexity/pplx-70b-online"
  #Groq Models
  - model_name: llama-3.1-8b-instant
    litellm_params:
      model: groq/llama-3.1-8b-instant
  - model_name: llama-3.1-70b-versatile
    litellm_params:
      model: groq/llama-3.1-70b-versatile
  - model_name: llama3-8b-8192
    litellm_params:
      model: groq/llama3-8b-8192
  - model_name: llama3-70b-8192
    litellm_params:
      model: groq/llama3-70b-8192
  - model_name: mixtral-8x7b-32768
    litellm_params:
      model: groq/mixtral-8x7b-32768
  #Github Models
  - model_name: github/llama-3.1-8b-instant
    litellm_params:
      model: github/llama-3.1-8b-instant
  - model_name: github/llama-3.1-70b-versatile
    litellm_params:
      model: github/llama-3.1-70b-versatile
  - model_name: github/llama3-8b-8192
    litellm_params:
      model: github/llama3-8b-8192
  - model_name: github/llama3-70b-8192
    litellm_params:
      model: github/llama3-70b-8192
  - model_name: github/mixtral-8x7b-32768
    litellm_params:
      model: github/mixtral-8x7b-32768
  - model_name: github/gemma-7b-it
    litellm_params:
      model: github/gemma-7b-it
  #Deepseek Models
  - model_name: deepseek-chat
    litellm_params:
      model: deepseek/deepseek-chat
  - model_name: deepseek-coder
    litellm_params:
      model: deepseek/deepseek-coder
  #Sagemaker Models (Commented out because your config will vary dramatically based on the specific model you are using. Refer to the docs: https://docs.litellm.ai/docs/providers/aws_sagemaker)
  - model_name: jumpstart-model
    #Databricks Models (Commented out because the api_base value will vary by user and needs to be manually updated)
    # - model_name: databricks-meta-llama-3-1-70b-instruct
    #   litellm_params:
    #     model: databricks/databricks-meta-llama-3-1-70b-instruct
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints

    # - model_name: databricks-mpt-7b-instruct
    #   litellm_params:
    #     model: databricks/databricks-mpt-7b-instruct
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints

    # - model_name: databricks-mpt-30b-instruct
    #   litellm_params:
    #     model: databricks/databricks-mpt-30b-instruct
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints

    # - model_name: databricks-mixtral-8x7b-instruct
    #   litellm_params:
    #     model: databricks/databricks-mixtral-8x7b-instruct
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints

    # - model_name: databricks-llama-2-70b-chat
    #   litellm_params:
    #     model: databricks/databricks-llama-2-70b-chat
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints

    # - model_name: databricks-meta-llama-3-70b-instruct
    #   litellm_params:
    #     model: databricks/databricks-meta-llama-3-70b-instruct
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints

    # - model_name: databricks-dbrx-instruct
    #   litellm_params:
    #     model: databricks/databricks-dbrx-instruct
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints

    # - model_name: databricks-meta-llama-3-1-405b-instruct
    #   litellm_params:
    #     model: databricks/databricks-meta-llama-3-1-405b-instruct
    #     api_base: "<Your databricks base url>" # e.g.: https://adb-3064715882934586.6.azuredatabricks.net/serving-endpoints
    litellm_params:
      model: sagemaker/llama-3-2-1b-instruct-2024-11-22-22-33-38-102
      hf_model_name: meta-llama/Llama-3.2-1B-Instruct
#Azure OpenAI Models (Commented out because the api_base and api_version values will vary by user and need to be manually updated)
# - model_name: azure/gpt-4o-realtime-preview-2024-10-01
#   litellm_params:
#     model: azure/gpt-4o-realtime-preview-2024-10-01
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"
# - model_name: azure/o1-mini
#   litellm_params:
#     model: azure/o1-mini
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/o1-preview
#   litellm_params:
#     model: azure/o1-preview
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4o-mini
#   litellm_params:
#     model: azure/gpt-4o-mini
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4o-mini-2024-07-18
#   litellm_params:
#     model: azure/gpt-4o-mini-2024-07-18
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4o
#   litellm_params:
#     model: azure/gpt-4o
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4o-2024-08-06
#   litellm_params:
#     model: azure/gpt-4o-2024-08-06
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4o-2024-05-13
#   litellm_params:
#     model: azure/gpt-4o-2024-05-13
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-turbo
#   litellm_params:
#     model: azure/gpt-4-turbo
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-turbo-preview
#   litellm_params:
#     model: azure/gpt-4-0125-preview
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-0125-preview
#   litellm_params:
#     model: azure/gpt-4-0125-preview
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-1106-preview
#   litellm_params:
#     model: azure/gpt-4-1106-preview
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-3.5-turbo
#   litellm_params:
#     model: azure/gpt-3.5-turbo
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-3.5-turbo-1106
#   litellm_params:
#     model: azure/gpt-3.5-turbo-1106
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-3.5-turbo-0301
#   litellm_params:
#     model: azure/gpt-3.5-turbo-0301
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-3.5-turbo-0613
#   litellm_params:
#     model: azure/gpt-3.5-turbo-0613
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-3.5-turbo-16k
#   litellm_params:
#     model: azure/gpt-3.5-turbo-16k
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-3.5-turbo-16k-0613
#   litellm_params:
#     model: azure/gpt-3.5-turbo-16k-0613
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4
#   litellm_params:
#     model: azure/gpt-4
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-0314
#   litellm_params:
#     model: azure/gpt-4-0314
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-0613
#   litellm_params:
#     model: azure/gpt-4-0613
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-32k
#   litellm_params:
#     model: azure/gpt-4-32k
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-32k-0314
#   litellm_params:
#     model: azure/gpt-4-32k-0314
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-32k-0613
#   litellm_params:
#     model: azure/gpt-4-32k-0613
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

# - model_name: azure/gpt-4-vision-preview
#   litellm_params:
#     model: azure/gpt-4-vision-preview
#     api_base: https://<your-resource-name>.openai.azure.com/
#     api_version: "<your api version>"

#Azure AI Studio Models (Commented out because the api_base value will vary by user and need to be manually updated)
# - model_name: azure_ai/Llama-3.1-70B-Instruct
#   litellm_params:
#     model: azure_ai/Llama-3.1-70B-Instruct
#     api_base: "<your azure ai base url>"

#Full details on guardrails here: https://docs.litellm.ai/docs/proxy/guardrails/bedrock
#You must attach the guardrail to your llm config by adding 
router_settings:
  routing_strategy: usage-based-routing-v2
  enable_pre_call_check: true
  context_window_fallbacks: [{"gpt-4": ["anthropic.claude-3-haiku-20240307-v1:0"]}, {"anthropic.claude-3-5-sonnet-20240620-v1:0": ["anthropic.claude-3-haiku-20240307-v1:0"]}] #Configure fallbacks for context window exeeded errors
  #fallbacks: [{"gpt-4o": ["anthropic.claude-3-5-sonnet-20240620-v1:0"]}] #Configure fallbacks for any other error
  #default_fallbacks: ["anthropic.claude-3-haiku-20240307-v1:0"] #Configure fallbacks for any error for every model (the above fallback configurations override this one)
guardrails:
  - guardrail_name: "bedrock-pre-guard"
    litellm_params:
      guardrail: bedrock
      mode: "during_call" # supported values: "pre_call", "post_call", "during_call"
      guardrailIdentifier: 6wcr934j0wgu # your guardrail ID on bedrock
      guardrailVersion: "1" # your guardrail version on bedrock
environment_variables:
  STORE_MODEL_IN_DB: 'True'
  LITELLM_LOG: "TRACE"
litellm_settings:
  cache: True
  cache_params:
    # type: redis-semantic
    # similarity_threshold: 0.8 # similarity threshold for semantic cache
    # redis_semantic_cache_embedding_model: text-embedding-ada-002 # only works with text-embedding-ada-002 for now... https://github.com/BerriAI/litellm/issues/4001
    type: redis
  max_budget: 1000000000.0 # (float) sets max budget in dollars across the entire proxy across all API keys. Note: the budget does not apply to the master key. That is the only exception.
  budget_duration: "1mo" # (str) frequency of budget reset - You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
  max_internal_user_budget: 1000000000.0 # (float) sets default budget in dollars for each internal user. (Doesn't apply to Admins. Doesn't apply to Teams. Doesn't apply to master key)
  internal_user_budget_duration: "1mo" # (str) frequency of budget reset - You can set duration as seconds ("30s"), minutes ("30m"), hours ("30h"), days ("30d"), months ("1mo").
  success_callback: ["s3"]
  failure_callback: ["s3"]
  service_callback: ["s3"]
  s3_callback_params:
    s3_region_name: us-west-2
    s3_bucket_name: logbucketcdkstack-litellmlogbucket3e0ea989-23jiy3pvw2gr
#ttl: Optional[float]
#default_in_memory_ttl: Optional[float]
#default_in_redis_ttl: Optional[float]