OpenAI-compatible drop-in

ChatGPT API Alternative

Same GPT models, lower per-token price. flatkey.ai is OpenAI-compatible — switch base_url in one line and keep your SDK, plus get Gemini, Claude, and DeepSeek on the same key with unified billing.

Get your API key See live pricing

GPT · Gemini · Claude · DeepSeek · Seedance — one key, one invoice · no credit card to start

Pricing vs official

GPT-5 output / 1M tokens	$6.67	$10.00
GPT-5 mini output / 1M tokens	$1.33	$2.00
GPT-5 input / 1M tokens	$0.83	$1.25

* Illustrative pricing — see the flatkey pricing page for live rates.

Switch base_url in one line

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://router.flatkey.ai/v1",
    api_key="YOUR_FLATKEY_KEY",
)

response = client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

curl

curl https://router.flatkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $FLATKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Same models, cheaper tokens

GPT models priced at roughly two-thirds of official, with top-up bonuses stacking further savings on every request.

One-line migration

Point your existing OpenAI SDK at a new base_url with a flatkey key. No new SDK, no request rewrites, no vendor lock-in.

Every major model on one key

GPT, Gemini, Claude, DeepSeek, and Seedance behind the same endpoint — swap the model id instead of managing five accounts.

Unified billing

One prepaid balance, usage analytics, and a single invoice across all providers instead of five separate bills.