---
title: "liter-llm"
description: "Universal LLM API client for 174 providers, chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server."
canonical: https://agentpluginsdirectory.com/plugins/liter-llm
last-updated: 2026-10-24
---

# liter-llm
Universal LLM API client for 174 providers, chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server.
- Slug: liter-llm
- Publisher: Kreuzberg, Inc.
- Repository: https://github.com/xberg-io/liter-llm
- Manifest: plugin/plugin.json
- Version: 2.4.0
- License: MIT
- Category (editorial): other
- Skills: 7 (liter-llm-calling-llms, liter-llm-embeddings-and-search, liter-llm-running-the-proxy, liter-llm-streaming-responses, liter-llm-tool-calling, liter-llm-using-the-mcp-server, liter-llm)
- MCP servers: 1 (liter-llm)
- Stars: 262
- Repository created: 2026-03-25
- Repository last pushed: 2026-10-24
- Publisher type: Organization
- Listing: https://agentpluginsdirectory.com/plugins/liter-llm
- Schema: https://agent-plugins.org/schemas/1.0.0/plugin.schema.json

## What liter-llm does, in the publisher's words

Universal LLM API client for 174 providers, chat, streaming, tools, embeddings, search, OCR, plus an OpenAI-compatible proxy and an MCP server, in your agent.

From the project README, punctuation lightly normalized. Full text: https://raw.githubusercontent.com/xberg-io/liter-llm/HEAD/plugin/README.md

## Skills

- liter-llm-calling-llms: Use when sending chat completions through liter-llm and routing to a specific provider via the `provider/model` prefix. Covers the chat call shape, provider routing, model_hint, message roles, and error categories.
- liter-llm-embeddings-and-search: Use when generating embeddings, calling the 12 web-search providers, or running OCR over documents with the 4 OCR providers through liter-llm. Covers embed, search, and ocr methods plus reranking.
- liter-llm-running-the-proxy: Use when running the `liter-llm api` OpenAI-compatible gateway, virtual keys, per-key rate limits, budgets, cost tracking, and model routing. Covers the TOML config and the 22 REST endpoints.
- liter-llm-streaming-responses: Use when streaming tokens incrementally from an LLM via liter-llm over SSE or async iterators. Covers chat_stream, delta handling, and null-content chunks.
- liter-llm-tool-calling: Use when defining functions/tools for an LLM to call through liter-llm, or requesting structured JSON outputs. Covers tool schemas, tool_calls handling, and response formats.
- liter-llm-using-the-mcp-server: Use when calling LLM APIs through the liter-llm MCP server's 22 tools, and to decide when MCP beats the CLI or SDK. Covers the tool surface, the auto-installing launcher, and authentication.
- liter-llm: Universal LLM API client for 174 providers with native bindings for 14 languages. Use when writing code that calls LLM APIs via liter-llm in Python, TypeScript, Rust, Go, Java, C#, Ruby, PHP, Elixir, WASM, or C, when running the OpenAI-compatible proxy, or when calling LLMs through the MCP server.…

Descriptions come from the frontmatter of each SKILL.md, punctuation lightly normalized.

## MCP servers

- liter-llm: transport: stdio; command: ./scripts/mcp-launch.sh mcp --transport stdio

Read from the plugin's own mcp.json. Environment variable names only, never values.