Quickstart

OpenKey is an OpenAI-compatible API. If your code talks to OpenAI, it talks to OpenKey — change the base URL and the key, keep everything else.

1. Get a key

Create a key from your dashboard. Keys are scoped, revocable, and never logged in plaintext.

2. Make a request

curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.5",
    "messages": [{"role": "user", "content": "Say hello."}]
  }'

Python (official OpenAI SDK):

from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)
resp = client.chat.completions.create(
    model="deepseek/deepseek-v3.2",
    messages=[{"role": "user", "content": "Say hello."}],
)
print(resp.choices[0].message.content)

TypeScript:

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.openkey.ai/v1',
  apiKey: process.env.OPENKEY_API_KEY,
});
const resp = await client.chat.completions.create({
  model: 'openai/gpt-5-mini',
  messages: [{ role: 'user', content: 'Say hello.' }],
});

3. Switch models by changing one string

Every model on the catalog is addressed as lab/model-slug. Same request shape for all of them. Streaming, tool calling, structured outputs, and vision work wherever the underlying model supports them — each model page lists exactly what’s supported.

What you pay

Provider list price + 3% flat. The math is on every model page and on /pricing. No credit-purchase fees, no spread between quoted and billed price.