Build on the same models.
Every endpoint behind one API key: OpenAI-compatible chat for language models, a queue for everything else, signed webhooks, and spending limits on every key.
Chat · Python Image · curl Video · curl import os
from openai import OpenAI
client = OpenAI(base_url=os.environ["FIXEDSEED_API"] + "/v1",
api_key=os.environ["FIXEDSEED_KEY"])
stream = client.chat.completions.create(
model="anthropic/claude-opus-5.5",
messages=[{"role": "user", "content": "Name a lighthouse café."}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="") Explore the API llms.txt