Faelith API
Change one URL. Keep your stack.
OpenAI-compatible Chat Completions for Echo and Horizon. Point your existing SDK at Faelith and ship this afternoon. You prepay credits, so the bill is a number you chose.
Try it right here
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.faelithindustries.com/v1",
api_key=os.environ["FAELITH_API_KEY"],
)
stream = client.chat.completions.create(
model="horizon",
messages=[{"role": "user", "content": "Find the race in this scheduler."}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="")Press Run to stream a response.Switch the language and the model, then run it. The cost uses the published rate card.
Everything you need, nothing you have to relearn
Drop-in compatible
Same request, same response, same streaming chunks. The official OpenAI SDKs work by changing the base URL.
Pay less for what repeats
Cached prompt tokens are billed at the cache-read rate, so long system prompts and agent loops get cheaper automatically.
A budget you set
API keys only spend prepaid credits and never touch plan allowances. Top up from $5 when you want.
From zero to first token
- 01
Create a key
In the dashboard, under API keys. Add credits in Spending.
- 02
Point your SDK
Set the base URL and key from the environment. No new client library.
- 03
Stream the answer
Reasoning arrives in delta.reasoning_content, the answer in delta.content, and usage at the end.
Questions people ask before switching
Which models can I call?
echo and horizon, both with a 1M-token context window.
Can I be charged more than I loaded?
No. When the wallet is empty the API answers 402 and stops; it never bills beyond your credits.
Where are the prices?
On the Models page, per 1M tokens, for input, output and every cache bucket.
Your SDK is already written. Just point it here.
Create a key, load a few dollars of credits and send your first request.