litellm vs ollama

A neutral, constraint-first comparison - live GitHub stats and typed relationships, not marketing.

litellmollama
TaglinePython SDK and Proxy Server for calling over 100 LLM APIs in OpenAI formatGet up and running with Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Stars53k176k
Forks9.5k17k
Open issues3.7k3.4k
LanguagePythonGo
LicenseOtherMIT
Last pushedJul 7, 2026Jul 7, 2026
CategoriesLLM Frameworks, Inference & ServingLLM Frameworks, AI Agents

litellm

A Python SDK along with a proxy server (AI Gateway) designed to facilitate the interaction with numerous large language models, providing functionalities like cost tracking, load balancing, guardrails, and logging across various providers such as Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM.

Python

ollama

Ollama is a platform for deploying and interacting with various large language models (LLMs) such as Kimi-K2.6, GLM-5.1, MiniMax, DeepSeek, gpt-oss, Qwen, and Gemma on macOS, Windows, Linux, and Docker environments.

Go