spb/tools-spboucher-ai

1{2  "slug": "litellm",3  "name": "LiteLLM",4  "aliases": ["litellm (PyPI)", "LiteLLM Proxy", "LiteLLM AI Gateway"],5  "vendor": { "name": "BerriAI", "slug": "berriai", "website": "https://www.litellm.ai" },6  "homepage_url": "https://www.litellm.ai/",7  "docs_url": "https://docs.litellm.ai/docs/",8  "repo_url": "https://github.com/BerriAI/litellm",9  "pricing_url": "https://www.litellm.ai/pricing",10  "license_url": "https://github.com/BerriAI/litellm/blob/main/LICENSE",11  "product_type": "library",12  "product_status": "active",13  "summary": "Open-source Python SDK and self-hosted AI gateway that calls 100+ LLM providers in the OpenAI format, with routing, fallbacks, virtual keys, budgets, spend tracking and logging callbacks",14  "description": "LiteLLM, from BerriAI, is an open-source project with two faces. The Python SDK offers one `completion()` interface that translates OpenAI-format requests to more than a hundred providers (OpenAI, Anthropic, Google, Bedrock, Azure, Mistral, Ollama, vLLM and many more), normalizes responses and exceptions, supports streaming and includes a Router for retries, fallbacks and load balancing across deployments. Callbacks forward inputs, outputs and computed cost to observability tools such as Langfuse, MLflow and Helicone.\n\nThe Proxy, also called the AI Gateway, packages the same translation layer as an OpenAI-compatible server for a whole organization: virtual API keys with per-key, per-team and per-user budgets, spend tracking across providers, caching, centralized logging, guardrails for content filtering and PII masking, an admin UI, an MCP gateway for tools and an agent gateway for A2A traffic, plus an auto-router that picks a model per request. A Rust-based gateway core is in beta. The core is MIT-licensed; an `enterprise/` directory under a separate license adds SSO/SAML, audit logs and multi-team management, sold as an enterprise offering. Deployment is Docker or CLI with a database for keys and spend.\n\nLiteLLM is the common answer when several teams need governed access to many providers from one internal endpoint, or when an application must stay provider-portable. Running the proxy adds operational components and a hop in the request path, provider-specific features are sometimes exposed with a lag, and the pace of releases means pinning versions in production.",15  "capabilities": ["Unified OpenAI-format `completion()` across 100+ providers", "Router with retries, fallbacks and load balancing", "OpenAI-compatible proxy server with virtual keys and budgets", "Spend tracking, caching and centralized logging", "Guardrails for content filtering and PII masking", "Callbacks to Langfuse, MLflow, Helicone and other observability tools", "MCP gateway, agent (A2A) gateway and auto-router", "Admin UI; Docker and CLI deployment; enterprise SSO and audit logs"],16  "workflows": ["Give each team a virtual key with a monthly budget on a shared gateway", "Fall back from one provider to another during an outage", "Keep an application portable by coding against the OpenAI format only", "Forward every call's cost to Langfuse for analysis"],17  "advantages": ["Very broad provider coverage", "MIT core with self-hosting", "Governance features (keys, budgets, logging) in one place", "Works as a library or as infrastructure"],18  "limitations": ["Proxy adds latency and operational components", "Enterprise features are separately licensed", "Provider feature parity can lag new releases", "Fast release cadence requires version pinning"],19  "prerequisites": ["Python 3.8+ for the SDK; Docker and a Postgres database for the proxy", "Provider API keys"],20  "audiences": ["Platform teams offering LLM access internally", "Developers who need provider portability", "Organizations tracking LLM spend per team"],21  "alternatives": ["openrouter", "langchain", "openai-platform", "langfuse"],22  "comparison_notes": "OpenRouter provides a similar unified API as a hosted service with its own billing, whereas LiteLLM is self-hosted software you run with your own provider keys. LangChain's model interface also abstracts providers but inside an application framework rather than as a gateway. Langfuse is complementary: LiteLLM commonly forwards traces and costs to it.",23  "categories": [{ "slug": "llm-ops", "primary": true }, { "slug": "model-providers", "label": "Gateway in front of many providers" }],24  "tags": ["llm", "api", "gateway", "open-source", "self-hosted", "python", "routing", "cost-tracking"],25  "use_cases": ["build-agents", "monitor-services", "serve-models"],26  "operating_systems": ["macos", "linux", "windows"],27  "execution_modes": ["local", "self-hosted"],28  "interfaces": ["library", "api", "cli", "web"],29  "deployment_models": ["embedded", "on-premises"],30  "integrations": ["OpenAI", "Anthropic", "Google Gemini", "Amazon Bedrock", "Azure OpenAI", "Mistral", "Ollama", "vLLM", "Langfuse", "MLflow", "PostgreSQL", "Redis", "Docker"],31  "data_formats": ["JSON", "YAML (proxy config)"],32  "languages": ["Python", "Rust (gateway core, beta)"],33  "source_model": "mixed",34  "license_spdx": "MIT",35  "pricing_model": ["open-source", "free", "enterprise"],36  "pricing_checked_at": "2026-11-02",37  "self_hostable": true,38  "sources": [39    { "url": "https://www.litellm.ai/", "type": "official_site", "title": "LiteLLM", "supports": ["name", "summary"], "checked_at": "2026-11-02" },40    { "url": "https://docs.litellm.ai/docs/", "type": "official_docs", "title": "LiteLLM documentation", "supports": ["capabilities", "integrations", "interfaces"], "checked_at": "2026-11-02" },41    { "url": "https://github.com/BerriAI/litellm/blob/main/LICENSE", "type": "license_page", "supports": ["license_spdx", "source_model"], "checked_at": "2026-11-02", "note": "MIT outside the enterprise/ directory, which has its own license" },42    { "url": "https://www.litellm.ai/pricing", "type": "pricing_page", "supports": ["pricing_model"], "checked_at": "2026-11-02" }43  ],44  "confidence": "high",45  "discovery_method": "editorial-research",46  "depth": "deep",47  "editorial_status": "reviewed",48  "visibility": "public",49  "featured": false,50  "author": "batch-A"51}52