OneCompression is a Python package for compressing large language models.
Open source
24 alternativesLiteLLM
LiteLLM provides a way to call more than 100 language models through an OpenAI-compatible interface.
About LiteLLM
LiteLLM provides a Python SDK and gateway for calling 100+ language models with OpenAI-style requests and responses. The SDK uses one completion() function across providers including OpenAI, Anthropic, Bedrock and Azure, with streaming, retries, fallbacks and per-call cost reporting. The gateway offers one endpoint for apps in different languages, with virtual keys that carry budgets and rate limits while recording requests and costs.
The same deployment can expose MCP servers and registered agent-to-agent endpoints with per-team access control. It also includes an Auto Router add-on that selects a model by cost for each request, a LiteAgents preview for switching agent harnesses with one parameter change, and a CLI and agent-based controls for managing keys, models and budgets. Single sign-on, SCIM, audit logs of admin changes and multi-region deployment require an Enterprise license.
Key features
- Call 100+ LLM providers with one OpenAI-format completion() function
- Issue virtual keys with budgets and rate limits
- Expose MCP servers from one endpoint with per-team access control
- Register A2A agents with per-team access, logs and cost tracking
- Send each request to a lower-cost model with Auto Router add-on
- Run Claude Code and Codex through the gateway via lite CLI
Best for: Developers and platform teams that manage multiple models, keys, budgets and tool access from one deployment.
Good for
- One OpenAI-compatible format works across SDK and gateway for many providers
- Central virtual keys, budgets, rate limits, logs and per-request costs
- Same deployment handles models, MCP tools and agent-to-agent calls
Watch out for
- Auto Router is listed as an add-on
- LiteAgents is listed as preview
- SSO, SCIM, audit logs and multi-region deployment need Enterprise license
LiteLLM at a glance
- Website
- docs.litellm.ai
- Type
- Online tool
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
LiteLLM alternatives
Tools and sites you could use instead, ranked by how closely they match.
The abso TypeScript SDK calls more than 100 LLM providers through an OpenAI compatible format.
Open source
24 alternatives
Chutes provides serverless compute for deploying, running, and scaling AI models through its platform and API.
This repository contains utilities intended for use with Llama models.
Notte provides cloud browser infrastructure and web automation for AI and coding agents.
PromptSite provides prompt version management for tracking, experimentation, and debugging LLM prompts.
Open source
24 alternativesPopular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioKili Technologykili-technology.comAPI docsdocs.x.aiEyePop.aieyepop.ai
LiteLLM FAQ
How do I change models in the Python SDK?
Change the model string in completion(); arguments stay the same and output uses OpenAI format.
How does the gateway track spending?
Each app or person uses a virtual key with a budget and rate limit; the gateway records each request and its cost.
How do I use Claude Code or Codex with the gateway?
Sign in with lite login, then start the tool through the gateway; budgets, logs and guardrails apply without individual provider keys.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.