Skip to main content
Orbitrage is a convenience layer between your code and the model providers. Point your existing OpenAI-compatible client at it and every call is routed to a cost-appropriate model and traced in your dashboard. No new SDK to learn, no telemetry pipeline to run. It speaks OpenAI format — to use Claude, Gemini, Grok, or any other model, you just name it; Orbitrage routes and translates behind the scenes.

​
Integrate with one prompt

Don’t want to wire it up by hand? Copy the prompt below and paste it into your AI coding agent (Cursor, Claude Code, Copilot, Windsurf, …) with “do this to my codebase.” It detects your language + framework, installs the SDK, and wires every LLM call — minimally and idiomatically.
Paste into your coding agent
Integrate Orbitrage (LLM router + full observability) into THIS codebase. Orbitrage is
OpenAI-API-compatible: existing OpenAI/Anthropic-style clients just point at
https://api.orbitrage.ai/v1 with an `orb_` key and every call is auto-routed + traced.
Make MINIMAL changes — only the integration, never the app logic. Docs: https://docs.orbitrage.ai

1) INSTALL the latest SDK (match the project language):
   • Python:  pip install -U orbitrage openai
   • Node/TS: npm install orbitrage@latest openai

2) INITIALIZE ONCE at the program entrypoint, before any LLM client is constructed. Read the
   key from env ORBITRAGE_API_KEY (never hardcode). Pass user_id = the end-user/customer id
   (use the real per-request id where available, else a sensible constant):
   • Python: import orbitrage; orbitrage.init(os.environ["ORBITRAGE_API_KEY"], user_id="<end_user_id>")
   • Node:   import { orbitrage } from "orbitrage";
             await orbitrage.init({ apiKey: process.env.ORBITRAGE_API_KEY, userId: "<end_user_id>" });

3) MODELS: prefer a DIRECT model for predictable behavior — "claude-sonnet-4-6" (quality) or
   "grok-4-fast" (fast/cheap). Use "auto" only to let Orbitrage pick the cheapest model, and
   then keep max_tokens >= 512 (auto may pick a reasoning model that truncates short answers).
   For Claude, do NOT use the Anthropic SDK — call model="claude-sonnet-4-6" via the OpenAI client.

4) WIRE every LLM client found in the repo:
   • Raw OpenAI SDK (OpenAI() / new OpenAI()): after init(), do NOT set base_url — init points it
     at the gateway and forces the orb_ key automatically (even if OPENAI_API_KEY is set). Only
     change the model id.
   • LangChain (Py):   ChatOpenAI(model="grok-4-fast", base_url="https://api.orbitrage.ai/v1",
       api_key=os.environ["ORBITRAGE_API_KEY"], default_headers={"x-orbitrage-end-user-id":"<id>"})
   • LangChain.js:     new ChatOpenAI({ model:"grok-4-fast", apiKey:process.env.ORBITRAGE_API_KEY,
       configuration:{ baseURL:"https://api.orbitrage.ai/v1",
                       defaultHeaders:{"x-orbitrage-end-user-id":"<id>"} } })
   • CrewAI:           LLM(model="openai/gpt-4o-mini", base_url="https://api.orbitrage.ai/v1",
       api_key=os.environ["ORBITRAGE_API_KEY"])   # LiteLLM validates names: use a recognized
       OpenAI id, or litellm.register_model({...}) to allow grok/claude.
   • Agno:             OpenAIChat(id="grok-4-fast", api_key=os.environ["ORBITRAGE_API_KEY"],
       base_url="https://api.orbitrage.ai/v1", default_headers={"x-orbitrage-end-user-id":"<id>"})
   • LlamaIndex:       from llama_index.llms.openai_like import OpenAILike
       OpenAILike(model="grok-4-fast", api_base="https://api.orbitrage.ai/v1",
                  api_key=os.environ["ORBITRAGE_API_KEY"], is_chat_model=True)  # stock OpenAI class
                  # rejects non-OpenAI model names — use OpenAILike for grok/claude/auto.
   • Vercel AI SDK:    createOpenAI({ baseURL:"https://api.orbitrage.ai/v1",
       apiKey:process.env.ORBITRAGE_API_KEY, headers:{"x-orbitrage-end-user-id":"<id>"} });
       then provider.chat("grok-4-fast")

5) MANAGED TOOLS (optional — no tool API keys to wire): add reserved names to the request
   tools array and Orbitrage runs them server-side: tavily_orbitrage (web search),
   serper_orbitrage, firecrawl_orbitrage, jina_orbitrage, weather_orbitrage,
   calculator_orbitrage, datetime_orbitrage. Pin a model (not "auto") for tool calls.

6) PER-USER (multi-tenant server): switch per request with orbitrage.set_user(id) (Python) /
   orbitrage.setUser(id) (Node), then construct a NEW client so it picks up the new id.

7) VERIFY: run the app; confirm calls succeed and show up at https://app.orbitrage.ai/workflows
   attributed to the user_id. For anything unclear or any edge case, consult https://docs.orbitrage.ai.
Get your orb_ key at app.orbitrage.ai → API Keys, then set ORBITRAGE_API_KEY in your environment before running the agent.

​
…or one line by hand

import orbitrage
orbitrage.init("orb_xxx", user_id=current_user.id)   # ← one line

from openai import OpenAI
OpenAI().chat.completions.create(
    model="grok-4-fast",                                          # auto for automatic routing
    messages=[{"role": "user", "content": "hi"}],
)
Pass user_id so you can see usage and cost per customer — it’s your own data about your own users. More →

​
What you get

Routing

model: "auto" picks the cheapest model that can handle the prompt.

Observability

Every call traced — model, tokens, cost, latency — automatically.

Bring your own key

Use your own provider credits for matching models.

Run it from Slack

Ask analytics, create projects and keys, get alerts — without the dashboard.

​
Start here

Quickstart

First call in 5 minutes.

Your framework

OpenAI, Anthropic, LangChain, CrewAI, and more.

Examples

Tool calling, streaming, per-user attribution.