v1.0 TypeScript Pythonsoon Rustsoon

One API for every
LLM provider — that you own

One typed interface across OpenAI, Anthropic, Google, and xAI — with dollar-cost tracking, observability, RAG, and agent governance built in. Direct to the providers: no gateway fee, no third party in your data path. A library you own, not a service you rent.

Get started Open Sandbox

quickstart.ts

import { complete } from '@combycode/llm-sdk';

const { text } = await complete({
  model: 'anthropic/claude-opus-4.8',
  apiKey: process.env.ANTHROPIC_KEY,
  prompt: 'Write a haiku about the sea.',
});

console.log(text);

Everything you need. Nothing you don't.

Built for teams who want unification as code they own — not another hop in the call chain.

◎

One package, every provider

Switch models with one string — OpenAI Responses, Anthropic Messages, Google generateContent, xAI — behind one prompt → result.text interface. A single dependencies:{} package replaces the stack you would otherwise hand-assemble from multiple provider SDKs.

◈

Your cost, your traffic

Per-call dollar cost + per-scope budgets, out of the box — from each provider’s own cost field where it returns one (xAI, OpenRouter), else a bundled versioned price catalog. Your keys go straight to the provider: no gateway take-rate (OpenRouter charges 5–5.5%), no third party in your data path, nothing to deploy.

◉

Observability & agents, built in

OTel-style traces, metrics, and logs emitted in-process (point them at Langfuse or any backend — no proxy hop), plus guardrails, human-in-the-loop, handoffs, RAG, and a built-in MCP client — unified across every provider. Elsewhere these come only as provider-locked frameworks or extra dependencies.

Official SDKs vs Gateways vs ORXA

Official SDKs are single-provider. Gateways unify, but add a per-request fee and route your traffic through a third party. ORXA gives you the unification as a library you own — direct to providers, no fee, with cost, observability, RAG, and agent governance built in across all of them.

See full comparison