ARLI API Documentation

OpenAI-compatible endpoint. 400+ AI models from 59 providers via OpenRouter — GPT, Claude, Gemini, DeepSeek, Qwen, GLM and more. One API key.

Quickstart

1. Register

curl -X POST https://arliwork.com/api/register \
  -H "Content-Type: application/json" \
  -d '{"email":"dev@company.com","password":"your_password","name":"Your Name"}'

Returns your api_key (arli-*) and litellm_key (sk-*). Both work. $1 free credit.

2. List Models

curl https://arliwork.com/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

3. Chat Completion

curl https://arliwork.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek-v4-flash",
  "messages": [{"role": "user", "content": "Hello"}]
}'

API Reference

Endpoint	Method	Description
`/v1/models`	GET	List all available models
`/v1/chat/completions`	POST	OpenAI-compatible chat completion
`/v1/agent/run` beta	POST	Autonomous agent task execution
`/api/register`	POST	Developer registration (returns API key)

Available Models

Provider	Models	Pricing (input / output per 1M tokens)
DeepSeek	v4-pro, v4-flash, r1, v3.2, chat	$0.10 – $0.70 / $0.20 – $2.50
Qwen (Alibaba)	3.7-max, 3.7-plus, 3-max, coder, coder-plus	$0.07 – $1.48 / $0.26 – $4.42
GLM (Zhipu)	5.2, 5.1, 5, 4.7, 4.6, vision	$0.06 – $0.97 / $0.40 – $3.04
Kimi (Moonshot)	k3, k2.7-code, k2.6, k2.5	$0.57 – $3.00 / $2.30 – $15.00
MiniMax	m3, m2.7, m2.5, m1	$0.15 – $0.55 / $0.90 – $2.20
ByteDance (Seed)	2.0-lite, 1.6, 1.6-flash	$0.07 – $0.25 / $0.30 – $2.00
Baidu (ERNIE)	4.5	$0.42 / $1.25
Tencent (Hunyuan)	hy3, a13b	$0.06 – $0.20 / $0.21 – $0.80
Xiaomi (Mimo)	v2.5-pro, v2.5	$0.14 – $0.44 / $0.28 – $0.87
Kwaipilot	kat-coder-pro-v2.5, v2	$0.30 – $0.74 / $1.20 – $2.96
Inception	mercury-2	$0.25 / $0.75
Aion Labs	3.0	$3.00 / $6.00
StepFun	3.7-flash	$0.20 / $1.15

Pricing Plans

Same four plans as the homepage.

Plan	Price
Free	$0/mo
Pro	$29/mo
Builder	$99/mo
Team	$249/mo

Enterprise: custom spend caps, SSO, SLA, on-prem — enterprise@arliwork.com

Authentication

All requests require a Bearer token. Two key types are supported:

arli-* — Platform API keys (full access: models, agents, sandbox)
sk-* — LiteLLM keys (model access only, OpenAI-compatible)

Get your key at arliwork.com/app/register.

OpenAI SDK Compatibility

Drop-in replacement — just change the base URL:

# Python
from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://arliwork.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Hello"}]
)

First day on ARLI (read this first)

Your first-generation agents will have rough edges — that's normal. Here's the supported path so you land on your feet:

0–5 min — Register, grab your API key from the playground, keep it in a vault. You start with $1 free credit.
5–20 min — Run the curl quickstart above. If it works, your endpoint + auth are correct.
Day 1 — Try one marketplace skill on a low-risk task. Watch how it behaves before wiring it into production.
Day 1–3 — Set a token/credit cap per agent so a runaway loop can't surprise you.
Week 1 — If you hit a bug, an edge case, or a billing question: report it. We ship fixes weekly and treat your feedback as the signal — not noise.

Support

Enterprise: enterprise@arliwork.com

Developer: hq@arliwork.com · Telegram t.me/arliwork

API Status: status.arliwork.com

We fix bugs weekly and publish a changelog. The first cohort's feedback is our fastest path to a product you can trust in week one, not month one.

Meet ARLI.