Ir al contenido
AI.info

AI Tools

LiteLLM

LiteLLM: precios, capacidades, actualizaciones y alternativas, leídos en las páginas del propio desarrollador.

El sitio web de LiteLLM

En inglés

Key facts

Price
Free plan · paid plans on request Read on litellm.ai
Free plan
Yes · Open Source Read on litellm.ai
Platforms
Web · macOS · Windows · Linux · CLI · API Read on litellm.ai
API
Yes Read on docs.litellm.ai
Open source
Yes Read on github.com
Certifications
SOC 2 Type II Read on docs.litellm.ai
Last update
15 Nov 2026 Read on docs.litellm.ai
Prices checked
25 Oct 2026 Read on litellm.ai

Developers can use the Python SDK to call different model providers through a common interface. Platform teams can run the gateway themselves to manage model access, keys, routing, budgets, rate limits, logging and request costs.

The open-source gateway is free to self-host. Enterprise adds features such as SSO, audit logs and support, with pricing quoted for the deployment. LiteLLM does not include the model providers’ inference; provider charges may apply.

Category
Developer Tools
Read from the maker’s pages
2026-11-18

Company

BerriAI

Features

  • Call multiple model providers through a shared OpenAI-compatible interface
  • Retry requests and route around failures with fallbacks and load balancing
  • Create virtual keys and set budgets or rate limits
  • Track request spend and usage across keys, users and teams
  • Log requests and connect observability integrations
  • Self-host a gateway with an admin UI
  • Open-source gateway and SDK under the MIT license

Use cases

  • Route an application’s requests across several model providers
  • Give engineering teams shared access to models through a self-hosted gateway
  • Set budgets and rate limits for teams or API keys
  • Switch providers or models without rewriting each integration
  • Monitor model request usage and cost across projects

Pricing

Free plan · paid plans on request

Prices checked
2026-10-25

Open Source

free

  • 100+ providers, one OpenAI API
  • Virtual keys, users & teams
  • Spend tracking
  • Budgets + rate limits
  • LLM fallbacks
  • Request/response logging

Enterprise

price on request

  • SSO + SCIM
  • OIDC / JWT auth
  • Audit logs
  • Secret managers + key rotation
  • Org & team admins
  • Multi-region control plane

Capabilities

  • Agent that edits files — “Agent SDK that routes every turn to the right model, across providers.” source
  • Choice of models — “Swap models without changing app code.” source
  • Self-hosted — “Self-host the same open-source gateway behind 240M+ Docker pulls, in your own cloud or fully air-gapped.” source
  • API — “One OpenAI-compatible API to 140+ providers and 1,800+ models.” source
  • Official SDKs — “Python SDK to call 100+ LLMs in the OpenAI format.” source
  • Builds agents and workflows — “Agent SDK that routes every turn to the right model, across providers.” source
  • Traces and evaluates — “Request/response logging” source

Latest updates

Where it works

Web · macOS · Windows · Linux · CLI · API

Security

  • SOC 2 Type II — “SOC 2 Type II. Our current report is available through the LiteLLM Trust Center .” source
  • SOC 2 — “SOC 2 Type II. Our current report is available through the LiteLLM Trust Center .” source

Alternatives to LiteLLM

  • Helicone

    Helicone routes, logs, and analyzes AI application requests, helping teams debug model calls, track costs, and manage prompts.

  • PRISMA AIRS AI Gateway

    Routes and governs AI traffic between applications, agents and model providers, with controls for security, usage and observability.

  • OpenRouter

    OpenRouter provides one API to access and route requests across AI models from multiple providers, with model selection, fallbacks, and usage tracking.

  • Dataiku LLM Mesh

    Dataiku LLM Mesh routes and governs access to hosted and self-hosted language models, with controls for usage, cost, performance, and safety.

  • MLflow

    MLflow helps teams track machine-learning work and build, evaluate, trace, and monitor LLM applications and agents.

  • Langfuse

    Langfuse traces AI applications, manages prompts, and evaluates model and agent outputs using cloud or self-hosted deployments.

Questions about LiteLLM

Is LiteLLM free?

Yes. LiteLLM has a free plan, called Open Source. Its other plans are priced on request. Prices checked on 25 Oct 2026.

How much does LiteLLM cost?

The plans on the maker’s pricing page: Open Source (free) and Enterprise (price on request). Prices checked on 25 Oct 2026.

Does LiteLLM have an API?

Yes. The maker’s pages state that LiteLLM has an API. Read on the maker’s pages on 18 Nov 2026.

Which platforms does LiteLLM run on?

LiteLLM runs on Web, macOS, Windows, Linux, CLI and API, as its maker’s pages state. Read on the maker’s pages on 18 Nov 2026.

Is LiteLLM open source?

Yes. The code of LiteLLM is published at github.com/BerriAI/litellm. Read on the maker’s pages on 18 Nov 2026.

Is LiteLLM still available?

Yes, as of 18 Nov 2026: its maker’s pages were read that day and carried no notice that LiteLLM has ended.

What changed recently in LiteLLM?

The latest entry in its maker’s changelog: 15 Nov 2026, “LiteLLM v1.110.0rc3 fixes fallback overrides and WebSocket model aliases”. Before it: 14 Nov 2026, “LiteLLM v1.107.0rc4 adds a CLI command to link GitHub Copilot accounts”. Changelog checked on 17 Nov 2026.

Sources

Official website