Magnus is built for agents that need to think, use tools, and get things done, without waiting around.
All 97 tasks of τ³-bench banking, head-to-head against gpt-5.6-sol, gpt-5.6-luna and gemini-3.7-flash, reasoning effort as published.
41.2% on τ³-bench banking, ahead of gpt-5.6-sol, with the field's best solve rate.
One flag between fast and thorough. 13.4 extra points when thinking is on, for 6 seconds.
55 seconds median per completed task, quicker than every model within ten points of it.
Celeris-1 is built for answers; Magnus is built for tasks. The API is the same, so switching is a one-word change.
Ultra-fast generation for chat, search and real-time interfaces.
Agentic work: tool loops, long tasks, structured actions.
The API is OpenAI-compatible. Point your SDK at inference.celeris.ai and keep the agent code you already wrote.
Sign up at console.celeris.ai. No waitlist, no sales call.
Keys are live immediately and billed per token.
Set the base URL and model id. Your existing agent code runs as is.
from openai import OpenAI
client = OpenAI(
base_url="https://inference.celeris.ai/celeris-1-magnus/v1",
api_key="ck_…",
)
resp = client.chat.completions.create(
model="celeris-1-magnus",
messages=[{"role": "user", "content": "Move my Friday payment to Monday"}],
tools=my_tools,
extra_body={"chat_template_kwargs": {"enable_thinking": True}},
)