Inference provider · Inference gateway (self-host)

LiteLLM

LiteLLM is an Inference gateway (self-host) in the 2026 agents.dancingteeth catalog. Self-hosted OpenAI-compatible gateway with routing, budgets, and observability across 100+ models.

Last updated

Verified

Best for

Self-hosted OpenAI-compatible gateway with routing, budgets, and observability across 100+ models.

Skip if

You want a paste-key hosted aggregator (OpenRouter/Requesty) with zero gateway ops.

Who it fits

  • Self-hosted OpenAI-compatible gateway with routing, budgets, and observability across 100+ models.
  • Builders who start in the browser without a local IDE setup
  • Terminal-first engineers who live in the shell and git
Experimental

Pros

Self-hostable OSS proxy/gateway routing 100+ models through one OpenAI-compatible API — load balancing, fallbacks, budgets, and observability for teams that want control vs a hosted aggregator.

Cons

You operate the gateway (Docker/K8s) — not a paste-key SaaS like OpenRouter; model keys still BYOK per provider; catalog has not hands-on verified production ops.

Facts

Locality:
Cloud-native
Surfaces:
Web, CLI
Maturity:
Experimental
BYOK:
Bring your own API key
Open source:
Source available
Free tier:
Free option available
Verified:
Sep 2026

Agent standards & memory

AGENTS.md: N/ASKILL.md: N/ARules / memory: LiteLLM proxy config; provider API keys in gateway env.100% Free (Open-source core); pay underlying model providers.

Compare one neighbor first

Vendor pages sell hard. Read one alternative on this site, then leave for the official link if the fit still holds.

Alternatives

Related tools

Frequently asked questions

What is LiteLLM?

LiteLLM is an Inference gateway (self-host) covered in the agents.dancingteeth 2026 catalog. Self-hostable OSS proxy/gateway routing 100+ models through one OpenAI-compatible API — load balancing, fallbacks, budgets, and observability for teams that want control vs a hosted aggregator.

Who is LiteLLM best for?

Self-hosted OpenAI-compatible gateway with routing, budgets, and observability across 100+ models.

When should I skip LiteLLM?

You want a paste-key hosted aggregator (OpenRouter/Requesty) with zero gateway ops.

What are the main trade-offs of LiteLLM?

Pros: Self-hostable OSS proxy/gateway routing 100+ models through one OpenAI-compatible API — load balancing, fallbacks, budgets, and observability for teams that want control vs a hosted aggregator. Cons: You operate the gateway (Docker/K8s) — not a paste-key SaaS like OpenRouter; model keys still BYOK per provider; catalog has not hands-on verified production ops.

Does LiteLLM support AGENTS.md, SKILL.md, or MCP?

This card lists AGENTS.md as N/A, SKILL.md as N/A, and rules/memory as LiteLLM proxy config; provider API keys in gateway env.. Free options: 100% Free (Open-source core); pay underlying model providers..

Someone asks you about vibe-coding software? Share this site with them — we are adding more useful data regularly. agents.dancingteeth.net

← Back to full tool directory