Get started with proxium

Who calls

Developercurl, OpenAI SDK

Coding agentClaude Code, Codex, Cursor · MCP

Your appOpenAI or Anthropic SDK

→

proxiumone base URLone virtual key

→

LLM APIs · your keys

• OpenAI
• Anthropic
• Groq
• OpenRouter
• Mistral
• DeepSeek
• Together AI
• Google Gemini
• your own server

Memory

Project memorycoding agents read and write it over MCP

a dashed box connects over MCP

proxium is an OpenAI-compatible gateway. Your apps send their model calls to proxium with one virtual key. proxium calls your provider with your own provider key. If a model fails, proxium tries the next model of the chain. It records the cost of each call.

Change two lines

Point the SDK that your app uses at https://proxium.tech/v1, and send your virtual key as the API key.

Python

app.py

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://proxium.tech/v1",
    api_key=os.environ["PROXIUM_KEY"],
)

answer = client.chat.completions.create(
    model=os.environ["PROXIUM_MODEL"],
    messages=[{"role": "user", "content": "Say hello in five words."}],
)
print(answer.choices[0].message.content)

Node

app.mjs

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://proxium.tech/v1",
  apiKey: process.env.PROXIUM_KEY,
});

const answer = await client.chat.completions.create({
  model: process.env.PROXIUM_MODEL,
  messages: [{ role: "user", content: "Say hello in five words." }],
});
console.log(answer.choices[0].message.content);

curl

curl https://proxium.tech/v1/chat/completions \
  -H "Authorization: Bearer $PROXIUM_KEY" \
  -H "Content-Type: application/json" \
  -d "{\"model\": \"$PROXIUM_MODEL\", \"messages\": [{\"role\": \"user\", \"content\": \"Say hello in five words.\"}]}"

PROXIUM_KEY is a virtual key of your project. PROXIUM_MODEL is a model id from GET /v1/models, or a tier name of your routing policy. The Quickstart shows how to get both.

Choose your path

QuickstartFrom a signed-in console to your first chat call.Use the OpenAI SDKPython, Node or plain HTTP: model names, streaming, embeddings.Use the Anthropic SDKSend Messages API calls through proxium.Connect an AI agentGive Claude Code, Codex, Cursor and others the project memory.ProvidersThe vendors that you can add with your own key.API referenceEvery endpoint that a virtual key can call.

What proxium does with a chat call

1. It finds the project of the virtual key.
2. It resolves the model field to a chain of models. See Routing.
3. It looks for the answer in the response cache. A cache hit makes no provider call and costs nothing by default. See The response cache.
4. It counts the call against the ceilings that you set for the calling application. See Budgets and limits.
5. It calls the models of the chain in order, with your provider key, until one answers.
6. It records the cost: the token counts from the answer, times the price of the model. See Track spend.

The full order, with the reason for each step, is in The request flow.