LiteLLM
LiteLLM is an open-source Python SDK and proxy server providing a unified OpenAI-compatible interface to 100+ LLM providers.
Limited machine-readable signal and partial portal coverage — documentation a human can read, but little a machine or agent can consume without scraping.
API Evangelist profiles LiteLLM the way a machine reads it — 39 machine-readable artifacts across 33 APIs, pulled from the provider's own public surface and indexed so a developer, an analyst, or an AI agent can evaluate it against every other provider on the network.
Every provider in the network is reduced to the same set of machine-readable artifacts — OpenAPI contracts, event specifications, GraphQL schemas, runnable collections, pricing and rate-limit signals, security posture, OAuth scopes, and the agent surfaces (MCP servers and skills) that let software drive the API on its own. We profile them because the interface is the part of a company you can actually inspect: it is a truer signal of what a provider does than any marketing page. From those artifacts we compute the Kin Score — LiteLLM scores 44.0/100 (thin), with a separate agent-readiness read of 48/100 (agent ready). The full breakdown is below, followed by every artifact we hold — each card links through to its machine-readable definition on apis.io.
Kin Score
This is the API Evangelist rating — a single, repeatable read computed from the artifacts on this page. Green fill is points earned; the red track is points possible, so every bar shows earned-versus-possible at a glance.
Kin Score
How this is scored →scored 2026-07-27 · rubric v0.5
How we profile LiteLLM
Each block below is one kind of artifact we hold for LiteLLM. For each we say what it is and why it earns a place in the profile, then list every one we've indexed — capped at two rows, scroll within the panel for the rest.
APIs 33
Each API is captured as its own OpenAPI definition — every operation, parameter, and response. This is the single most useful machine-readable description of what an API does, and it's what lets us score, lint, mock, and generate against it without asking the provider for anything.
Individual APIs this provider publishes, each with its own machine-readable definition.
LiteLLM Completions API
Provides an OpenAI-compatible /completions endpoint for text completion requests routed through the LiteLLM proxy to supported LLM providers.
LiteLLM Responses API
Provides an OpenAI-compatible /responses endpoint supporting the Responses API specification, including conversation history compression via /responses/compact.
LiteLLM Embeddings API
Provides an OpenAI-compatible /embeddings endpoint for generating text embeddings across multiple providers including OpenAI, Cohere, HuggingFace, and Bedrock with unified forma...
LiteLLM Image Generation API
Provides OpenAI-compatible /images/generations, /images/edits, and /images/variations endpoints for image generation and manipulation routed through the LiteLLM proxy.
LiteLLM Audio API
Provides OpenAI-compatible /audio/transcriptions and /audio/speech endpoints for audio transcription and text-to-speech conversion across supported providers.
LiteLLM Moderations API
Provides an OpenAI-compatible /moderations endpoint for content moderation across supported providers through the LiteLLM proxy.
LiteLLM Batches API
Provides an OpenAI-compatible /batches endpoint for batch processing operations, enabling bulk request handling across LLM providers.
LiteLLM Files API
Provides an OpenAI-compatible /files endpoint for file management operations used in conjunction with fine-tuning and batch processing.
LiteLLM Fine-Tuning API
Provides an OpenAI-compatible /fine_tuning endpoint for model fine-tuning operations across supported providers through the LiteLLM proxy.
LiteLLM Rerank API
Provides a /rerank endpoint for document reranking operations, supporting providers like Cohere through the LiteLLM proxy with a unified interface.
LiteLLM Vector Stores API
Provides /vector_stores endpoints for creating and managing vector stores, file operations within vector stores, and search functionality for retrieval-augmented generation (RAG...
LiteLLM Anthropic Messages API
Provides Anthropic-compatible /v1/messages and /v1/messages/count_tokens endpoints for native Anthropic API format support through the LiteLLM proxy.
LiteLLM Realtime API
Provides /realtime WebSocket endpoints for real-time model interactions with load balancing and guardrails support across providers.
LiteLLM MCP API
Provides /mcp endpoints for Model Context Protocol (MCP) integration, enabling LLMs to interact with external tools and APIs through OpenAPI specifications.
LiteLLM OCR API
Provides an /ocr endpoint for optical character recognition, enabling text extraction from images through supported providers via the LiteLLM proxy.
LiteLLM Guardrails API
Provides /guardrails/apply_guardrail endpoint for applying configured content filtering and safety guardrails to LLM requests and responses.
LiteLLM Evals API
Provides /evals endpoints for the Evaluations API, enabling measurement and benchmarking of model performance through the LiteLLM proxy.
LiteLLM A2A Agent Gateway API
Provides /a2a endpoints for the Agent-to-Agent (A2A) gateway, enabling agent registration, publishing, and inter-agent communication.
LiteLLM Videos API
Provides /videos endpoints for video generation and handling through supported providers like RunwayML via the LiteLLM proxy.
LiteLLM Assistants API
The Assistants API from LiteLLM — 1 operation(s) for assistants.
LiteLLM Audio API
The Audio API from LiteLLM — 2 operation(s) for audio.
LiteLLM Batches API
The Batches API from LiteLLM — 1 operation(s) for batches.
LiteLLM Chat API
The Chat API from LiteLLM — 1 operation(s) for chat.
LiteLLM Completions API
The Completions API from LiteLLM — 1 operation(s) for completions.
LiteLLM Embeddings API
The Embeddings API from LiteLLM — 1 operation(s) for embeddings.
LiteLLM Fine Tuning API
The Fine Tuning API from LiteLLM — 1 operation(s) for fine tuning.
LiteLLM Images API
The Images API from LiteLLM — 3 operation(s) for images.
LiteLLM Messages API
The Messages API from LiteLLM — 2 operation(s) for messages.
LiteLLM Moderations API
The Moderations API from LiteLLM — 1 operation(s) for moderations.
LiteLLM Ocr API
The Ocr API from LiteLLM — 1 operation(s) for ocr.
LiteLLM Rag API
The Rag API from LiteLLM — 2 operation(s) for rag.
LiteLLM Rerank API
The Rerank API from LiteLLM — 1 operation(s) for rerank.
LiteLLM Vector Stores API
The Vector Stores API from LiteLLM — 2 operation(s) for vector stores.
Scroll within the panel for all 33 ·
Open Collections 1
Open, tool-agnostic collections carry the same runnable value as Postman without locking you to one client — the portable, forkable form of the same exercise.
Open, tool-agnostic API collections (OpenAPI-derived and Bruno).
LiteLLM Proxy API
OPEN COLLECTIONPricing Plans 1
Pricing is part of the interface. Machine-readable plans tell you what a tier costs and includes before you commit — one of the six things the Kin Score reads for commercial clarity.
Published pricing tiers and plan structures.
Rate Limits 1
Rate limits are the difference between a demo that works and a production integration that doesn't fall over. Publishing them is an operational-transparency signal — and a hard requirement for any agent that plans its own throughput.
Documented rate limits and quota policies.
Litellm Rate Limits
RATE LIMITSFinOps 1
Cost, billing, and metering signals let a buyer model the financial operations of an API before it's live. We profile them for the same reason we profile pricing: the money is part of the contract.
Cost, billing, and metering signals for API financial operations.
Litellm Finops
FINOPSSecurity Posture 1
Authentication, domain security, vulnerability disclosure, and trust-center signals — the evidence that a provider takes security seriously enough to document it. We profile it because you can't govern what you can't see.
Authentication, domain security, vulnerability disclosure, and trust-center signals.
Agentic Access 1
An x-agentic-access contract marks which operations are safe for an agent to run on its own and which need a human in the loop. It is the difference between an API an agent can use and one it can use safely.
Recommended x-agentic-access execution contracts for AI agents.
Resources
Every other property we hold for LiteLLM — documentation, portals, status pages, policies, and corporate surface — grouped by the job it does, following the integrator's arc from getting started to running in production.
Get Started 2
Portal, sign-up, and the first successful call
Documentation 1
Reference material describing how the API behaves
Agent Surfaces 2
MCP servers, agent skills, and machine-readable catalogs
Build 1
SDKs, sample code, and the tooling you integrate with
Access & Security 2
Authentication, authorization, and security posture
Operate 5
Status, limits, changes, and where to get help
Commercial 1
Pricing, plans, and the legal terms of use
Company 2
The organization behind the API
Other 9
Properties that don't map to a standard resource type
Scroll within the panel for all 9 ·
← All providers · Data indexed from github.com/api-evangelist/litellm · machine-readable index on apis.io