# Litellm

> Documentation for Litellm

## Pages

- [Docs 10 Documentation](docs-10-documentation.md)
- [https://docs.litellm.ai/ llms-full.txt](httpsdocslitellmai-llms-fulltxt.md)
- [LiteLLM - Getting Started](litellm-getting-started.md): - Translate inputs to provider's`completion`,`embedding`, and`image_generation`endpoints
- [auth: run 'gcloud auth application-default'](auth-run-gcloud-auth-application-default.md): os.environ["VERTEX_PROJECT"] = "hardy-device-386718"
- [e.g. Call 'WizardLM/WizardCoder-Python-34B-V1.0' hosted on HF Inference endpoints](eg-call-wizardlmwizardcoder-python-34b-v10-hosted-on-hf-inference-endpoints.md): response = completion(
- [azure call](azure-call.md): response = completion(
- [auth: run 'gcloud auth application-default'](auth-run-gcloud-auth-application-default-2.md): os.environ["VERTEX_PROJECT"] = "hardy-device-386718"
- [e.g. Call 'WizardLM/WizardCoder-Python-34B-V1.0' hosted on HF Inference endpoints](eg-call-wizardlmwizardcoder-python-34b-v10-hosted-on-hf-inference-endpoints-2.md): response = completion(
- [azure call](azure-call-2.md): response = completion(
- [set callbacks](set-callbacks.md): litellm.success_callback = ["lunary", "mlflow", "langfuse", "helicone"] # log input/output to lunary, mlflow, langfus...
- [track_cost_callback](track-cost-callback.md): def track_cost_callback(
- [set callback](set-callback.md): litellm.success_callback = [track_cost_callback] # set custom callback function
- [litellm.completion() call](litellmcompletion-call.md): response = completion(
- [request sent to model set on litellm proxy, `litellm --model`](request-sent-to-model-set-on-litellm-proxy-litellm-model.md): response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [\
- [Completion Function - completion()](completion-function-completion.md): The Input params are **exactly the same** as the
- [Request Body](request-body.md): **Required Fields**
- [Completion Function - completion()](completion-function-completion-2.md): Here's the exact json output you can expect from a litellm`completion`call:
- [Generation/Completion/Chat Completion Models](generationcompletionchat-completion-models.md): | Model Name | Function Call | Required OS Variables |
- [Contact Us](contact-us.md): - [Meet with us 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Contributing to Documentation](contributing-to-documentation.md): Clone litellm
- [Embedding Models](embedding-models.md): | Model Name | Function Call | Required OS Variables |
- [Tutorial Intro](tutorial-intro.md): Let's discover **Docusaurus in less than 5 minutes**.
- [Callbacks](callbacks.md): liteLLM provides`success_callbacks`and`failure_callbacks`, making it easy for you to send data to a particular pro...
- [set callbacks](set-callbacks-2.md): litellm.success_callback=["posthog", "helicone", "lunary"]
- [Helicone Tutorial](helicone-tutorial.md): [Helicone](https://helicone.ai/) is an open source observability platform that proxies your OpenAI traffic and provid...
- [set callbacks](set-callbacks-3.md): litellm.success_callback=["helicone"]
- [Supabase Tutorial](supabase-tutorial.md): [Supabase](https://supabase.com/) is an open source Firebase alternative.
- [set callbacks](set-callbacks-4.md): litellm.success_callback=["supabase"]
- [0 Critical/High Vulnerabilities](0-criticalhigh-vulnerabilities.md): - LiteLLMBase image now uses`cgr.dev/chainguard/python:latest-dev`
- [Use the provided base image](use-the-provided-base-image.md): FROM ghcr.io/berriai/litellm:main-latest
- [Install dependencies - CHANGE THIS to `apk`](install-dependencies-change-this-to-apk.md): RUN apt-get update && apt-get install -y dumb-init
- [set api keys](set-api-keys.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [Tags](tags.md): - [admin ui3](https://docs.litellm.ai/release_notes/tags/admin-ui)
- [set api keys](set-api-keys-2.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [set api keys](set-api-keys-3.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [set api keys](set-api-keys-4.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [0 Critical/High Vulnerabilities](0-criticalhigh-vulnerabilities-2.md): - LiteLLMBase image now uses`cgr.dev/chainguard/python:latest-dev`
- [Use the provided base image](use-the-provided-base-image-2.md): FROM ghcr.io/berriai/litellm:main-latest
- [Install dependencies - CHANGE THIS to `apk`](install-dependencies-change-this-to-apk-2.md): RUN apt-get update && apt-get install -y dumb-init
- [set api keys](set-api-keys-5.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [0 Critical/High Vulnerabilities](0-criticalhigh-vulnerabilities-3.md): - LiteLLMBase image now uses`cgr.dev/chainguard/python:latest-dev`
- [Use the provided base image](use-the-provided-base-image-3.md): FROM ghcr.io/berriai/litellm:main-latest
- [Install dependencies - CHANGE THIS to `apk`](install-dependencies-change-this-to-apk-3.md): RUN apt-get update && apt-get install -y dumb-init
- [Litellm Documentation](litellm-documentation.md)
- [https://docs.litellm.ai/ llms-full.txt](httpsdocslitellmai-llms-fulltxt-2.md)
- [LiteLLM - Getting Started](litellm-getting-started-2.md): - Translate inputs to provider's`completion`,`embedding`, and`image_generation`endpoints
- [auth: run 'gcloud auth application-default'](auth-run-gcloud-auth-application-default-2.md): os.environ["VERTEX_PROJECT"] = "hardy-device-386718"
- [e.g. Call 'WizardLM/WizardCoder-Python-34B-V1.0' hosted on HF Inference endpoints](eg-call-wizardlmwizardcoder-python-34b-v10-hosted-on-hf-inference-endpoints-2.md): response = completion(
- [azure call](azure-call-2.md): response = completion(
- [auth: run 'gcloud auth application-default'](auth-run-gcloud-auth-application-default-2-2.md): os.environ["VERTEX_PROJECT"] = "hardy-device-386718"
- [e.g. Call 'WizardLM/WizardCoder-Python-34B-V1.0' hosted on HF Inference endpoints](eg-call-wizardlmwizardcoder-python-34b-v10-hosted-on-hf-inference-endpoints-2-2.md): response = completion(
- [azure call](azure-call-2-2.md): response = completion(
- [set callbacks](set-callbacks-2.md): litellm.success_callback = ["lunary", "mlflow", "langfuse", "helicone"] # log input/output to lunary, mlflow, langfus...
- [track_cost_callback](track-cost-callback-2.md): def track_cost_callback(
- [set callback](set-callback-2.md): litellm.success_callback = [track_cost_callback] # set custom callback function
- [litellm.completion() call](litellmcompletion-call-2.md): response = completion(
- [request sent to model set on litellm proxy, `litellm --model`](request-sent-to-model-set-on-litellm-proxy-litellm-model-2.md): response = client.chat.completions.create(model="gpt-3.5-turbo", messages = [\
- [Completion Function - completion()](completion-function-completion-2.md): The Input params are **exactly the same** as the
- [Request Body](request-body-2.md): **Required Fields**
- [Completion Function - completion()](completion-function-completion-2-2.md): Here's the exact json output you can expect from a litellm`completion`call:
- [Generation/Completion/Chat Completion Models](generationcompletionchat-completion-models-2.md): | Model Name | Function Call | Required OS Variables |
- [Contact Us](contact-us-2.md): - [Meet with us 👋](https://calendly.com/d/4mp-gd3-k5k/berriai-1-1-onboarding-litellm-hosted-version)
- [Contributing to Documentation](contributing-to-documentation-2.md): Clone litellm
- [Embedding Models](embedding-models-2.md): | Model Name | Function Call | Required OS Variables |
- [Tutorial Intro](tutorial-intro-2.md): Let's discover **Docusaurus in less than 5 minutes**.
- [Callbacks](callbacks-2.md): liteLLM provides`success_callbacks`and`failure_callbacks`, making it easy for you to send data to a particular pro...
- [set callbacks](set-callbacks-2-2.md): litellm.success_callback=["posthog", "helicone", "lunary"]
- [Helicone Tutorial](helicone-tutorial-2.md): [Helicone](https://helicone.ai/) is an open source observability platform that proxies your OpenAI traffic and provid...
- [set callbacks](set-callbacks-3-2.md): litellm.success_callback=["helicone"]
- [Supabase Tutorial](supabase-tutorial-2.md): [Supabase](https://supabase.com/) is an open source Firebase alternative.
- [set callbacks](set-callbacks-4-2.md): litellm.success_callback=["supabase"]
- [0 Critical/High Vulnerabilities](0-criticalhigh-vulnerabilities-2.md): - LiteLLMBase image now uses`cgr.dev/chainguard/python:latest-dev`
- [Use the provided base image](use-the-provided-base-image-2.md): FROM ghcr.io/berriai/litellm:main-latest
- [Install dependencies - CHANGE THIS to `apk`](install-dependencies-change-this-to-apk-2.md): RUN apt-get update && apt-get install -y dumb-init
- [set api keys](set-api-keys-2.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [Tags](tags-2.md): - [admin ui3](https://docs.litellm.ai/release_notes/tags/admin-ui)
- [set api keys](set-api-keys-2-2.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [set api keys](set-api-keys-3-2.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [set api keys](set-api-keys-4-2.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [0 Critical/High Vulnerabilities](0-criticalhigh-vulnerabilities-2-2.md): - LiteLLMBase image now uses`cgr.dev/chainguard/python:latest-dev`
- [Use the provided base image](use-the-provided-base-image-2-2.md): FROM ghcr.io/berriai/litellm:main-latest
- [Install dependencies - CHANGE THIS to `apk`](install-dependencies-change-this-to-apk-2-2.md): RUN apt-get update && apt-get install -y dumb-init
- [set api keys](set-api-keys-5-2.md): os.environ["DEEPGRAM_API_KEY"] = ""
- [0 Critical/High Vulnerabilities](0-criticalhigh-vulnerabilities-3-2.md): - LiteLLMBase image now uses`cgr.dev/chainguard/python:latest-dev`
- [Use the provided base image](use-the-provided-base-image-3-2.md): FROM ghcr.io/berriai/litellm:main-latest
- [Install dependencies - CHANGE THIS to `apk`](install-dependencies-change-this-to-apk-3-2.md): RUN apt-get update && apt-get install -y dumb-init