A unified, OpenAI-compatible HTTP API for 200+ models from 40+ providers (OpenAI, Anthropic, Google, DeepSeek, Mistral). Drop-in replacement for the OpenAI Python and Node.js SDKs. Per-API-key budgets, rate limiting, usage analytics, and a developer dashboard.
One key to access all providers. No more managing multiple accounts and billing systems.
No monthly commitments. Only pay for what you use at transparent, competitive rates.
Automatic failover between providers. If one is down, we route to the next best option.
Track every request, token, and dollar. Detailed logs with model, latency, and cost breakdowns.
Per-key rate limits protect your budget. Set RPM and RPD limits for each API key.
Drop-in replacement for OpenAI's API. Works with any SDK, library, or tool that supports OpenAI.
from openai import OpenAI
client = OpenAI(
api_key="maxai-your-key-here",
base_url="https://maxai.is-a.dev/v1"
)
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)Drop-in replacement for the OpenAI SDK. Just change the base URL.
curl https://maxai.is-a.dev/v1/chat/completions \
-H "Authorization: Bearer maxai-your-key" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-mini",
"messages": [{"role": "user", "content": "Hello!"}]
}'import OpenAI from "openai";
const client = new OpenAI({
apiKey: "maxai-your-key",
baseURL: "https://maxai.is-a.dev/v1",
});
const r = await client.chat.completions.create({
model: "claude-haiku-4-5",
messages: [{ role: "user", content: "Hello!" }],
});Standard Authorization: Bearer maxai-... header. No SDK lock-in.
Server-Sent Events (text/event-stream) supported on every chat-completions endpoint.
Programmatic /api/usage/* endpoints for cost, tokens, and per-model latency.
Built-in workflow templates (chatbot, summarizer, translator, code-review, classifier, moderation).
Start free. Scale as you grow. No hidden fees.