Repository avatar
AI Tools
v1.0.0
active

mcp

com.martllm/mcp

One API key for every AI model, usually below list price.

Documentation

MartLLM

MartLLM

Formerly UberLLM: same service, same accounts and API keys. The old uberllm.dev addresses keep working.

MartLLM is an API marketplace for AI models: chat, image, video, music and speech. You call one OpenAI- and Anthropic-compatible API with one key. Each request is served by a third-party inference provider for that model, and costs what that provider charged for it.

  • No MartLLM fee on requests. Adding credit by card costs 5.5% + $0.50.
  • Prepaid. Accounts start at $0; a request that fails is not billed.
  • Base URL: https://api.martllm.com/v1 (OpenAI) or https://api.martllm.com (Anthropic).
  • Models and live prices: https://martllm.com/models
  • Docs: https://martllm.com/docs

This repository holds the public tooling: plugins for Claude Code and Codex, a Gemini CLI extension, the uberllm agent skill, the Claude Code installer with its checksums, and copy-paste setup for SDKs and MCP clients.

Get a key

Sign in at https://martllm.com with your email (a code is sent, no password), add credit, and create a key in Dashboard → Keys. Keys start with ull_.

Install in your coding agent

This repository is a Claude Code plugin, a Codex plugin, a Gemini CLI extension and an Agent Skill. Each one adds MartLLM's hosted MCP server (https://api.martllm.com/mcp, Streamable HTTP) and/or the uberllm skill, which knows how to set MartLLM up, pick a model and make images and videos. Nothing to build or run locally: the server is hosted, and it authenticates with your key as Authorization: Bearer ull_....

MCP tools: list_models, get_model, quote, generate_image, edit_image, start_video, get_job, wait_job, balance. A tool call is billed exactly like the same API request. Full reference: https://martllm.com/docs/mcp

Claude Code plugin (MCP server + skill). Inside Claude Code:

/plugin marketplace add al-global-tech/martllm
/plugin install uberllm@uberllm

Claude Code asks for your API key when the plugin is enabled and keeps it in your system's credential store. Set or change it later with claude plugin configure uberllm.

Codex plugin (MCP server + skill):

codex plugin marketplace add al-global-tech/martllm
codex plugin add uberllm@uberllm
export UBERLLM_API_KEY=ull_...   # the MCP server reads the key from here

Gemini CLI extension (MCP server + skill):

gemini extensions install https://github.com/al-global-tech/martllm

Gemini CLI asks for your API key on install and keeps it in your system keychain (change it with gemini extensions config uberllm). If you skip it, export UBERLLM_API_KEY=ull_... before starting gemini works too.

Skill only (Claude Code, Codex, Cursor, OpenCode and other agents that read Agent Skills), via skills.sh:

npx skills add al-global-tech/martllm

MCP server only, Claude Code:

claude mcp add --transport http uberllm https://api.martllm.com/mcp --header "Authorization: Bearer ull_..."

Cursor (~/.cursor/mcp.json) and other clients that take a URL:

{
  "mcpServers": {
    "uberllm": {
      "url": "https://api.martllm.com/mcp",
      "headers": { "Authorization": "Bearer ull_..." }
    }
  }
}

Cline (MCP Servers → Configure MCP Servers, which opens cline_mcp_settings.json). Set "type": "streamableHttp": without a type, Cline connects over SSE and the server does not answer that way. Step-by-step instructions for Cline and other agents: llms-install.md.

{
  "mcpServers": {
    "uberllm": {
      "type": "streamableHttp",
      "url": "https://api.martllm.com/mcp",
      "headers": { "Authorization": "Bearer ull_..." },
      "disabled": false
    }
  }
}

VS Code (.vscode/mcp.json; VS Code asks for the key once and stores it):

{
  "inputs": [
    { "type": "promptString", "id": "uberllm-key", "description": "MartLLM API key (ull_...)", "password": true }
  ],
  "servers": {
    "uberllm": {
      "type": "http",
      "url": "https://api.martllm.com/mcp",
      "headers": { "Authorization": "Bearer ${input:uberllm-key}" }
    }
  }
}

Claude Desktop (Settings → Developer → Edit Config), through mcp-remote:

{
  "mcpServers": {
    "uberllm": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://api.martllm.com/mcp", "--header", "Authorization:${UBERLLM_AUTH}"],
      "env": { "UBERLLM_AUTH": "Bearer ull_..." }
    }
  }
}

The server is listed in the official MCP Registry as dev.uberllm/mcp (server.json).

OpenAI SDK

from openai import OpenAI

client = OpenAI(base_url="https://api.martllm.com/v1", api_key="ull_...")
r = client.chat.completions.create(
    model="deepseek/deepseek-v4-flash",
    messages=[{"role": "user", "content": "Say hello in five words."}],
)
print(r.choices[0].message.content)

Anthropic SDK

from anthropic import Anthropic

client = Anthropic(base_url="https://api.martllm.com", api_key="ull_...")
m = client.messages.create(
    model="anthropic/claude-haiku-4.5",
    max_tokens=100,
    messages=[{"role": "user", "content": "Say hello in five words."}],
)
print(m.content[0].text)

Any chat model in the catalog works on both APIs. Model ids are the ids on https://martllm.com/models.

Vercel AI SDK

import { createOpenAICompatible } from "@ai-sdk/openai-compatible";
import { generateText } from "ai";

const uberllm = createOpenAICompatible({
  name: "uberllm",
  apiKey: process.env.UBERLLM_API_KEY,
  baseURL: "https://api.martllm.com/v1",
  includeUsage: true,
});

const { text } = await generateText({
  model: uberllm("deepseek/deepseek-v4-flash"),
  prompt: "Say hello in five words.",
});

Streaming, tool calls and images: https://martllm.com/docs/ai-sdk

More examples and packages

  • cookbook/: runnable examples for the OpenAI and Anthropic SDKs, LangChain, LlamaIndex, LiteLLM, Pydantic AI, CrewAI, Instructor, DSPy, the Vercel AI SDK, Mastra, Go, Rust, Spring AI, .NET and curl, plus images, video, music and speech. Each one was run against the live API.
  • langchain-uberllm: ChatUberLLM for LangChain (Python).
  • ai-sdk-provider-uberllm: MartLLM provider for the Vercel AI SDK.
  • llm-uberllm: plugin for Simon Willison's llm command-line tool.

Claude Code

By hand (3 steps)

  1. Create a key in Dashboard → Keys.

  2. Save it to a file only you can read:

    mkdir -p ~/.uberllm && chmod 700 ~/.uberllm
    printf '%s\n' 'ull_your_key' > ~/.uberllm/key && chmod 600 ~/.uberllm/key
    
  3. Add this to ~/.claude/settings.json (every project) or <project>/.claude/settings.local.json (one project):

    {
      "apiKeyHelper": "cat ~/.uberllm/key",
      "env": {
        "ANTHROPIC_BASE_URL": "https://api.martllm.com",
        "CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY": "1"
      }
    }
    

With the installer

install/claude-code.sh (macOS, Linux) and install/claude-code.ps1 (Windows) are byte-for-byte the files served at https://martllm.com/install/. They sign you in through the browser, save the key to a mode-600 file, merge ANTHROPIC_BASE_URL and an apiKeyHelper into your Claude Code settings (backing the file up first), and make one test request. --uninstall reverts it.

Read it, check it, then run it:

curl -fsSL https://martllm.com/install/claude-code.sh -o claude-code.sh
shasum -a 256 claude-code.sh   # compare with install/SHA256SUMS
less claude-code.sh
sh claude-code.sh              # add --project for this project only
FileSHA-256
claude-code.shf5aa1c4610992d8f4ecc1b1cd777bc731c5fad9da6a38cac46989834b194d66c
claude-code.ps160d631b48e60a2e3f17e5eee19136d47a255f143627986e86b6ceb379858a3b9

If the file you downloaded does not match the sum above, do not run it, and tell us at support@uberllm.dev.

Details: https://martllm.com/docs/claude-code

Support

support@uberllm.dev · Privacy · Terms

License

MIT

No installation packages available.

Remote