SERVE · SERVERLESS, DEDICATED AND RESERVED

Private endpoints your SDK already speaks

Swap your OpenAI or Anthropic base URL. The rest of your code stays the same. Run it on serverless, dedicated or reserved capacity.

PythonTypeScriptcURL
from openai import OpenAI

client = OpenAI(
    base_url="https://api.nucleus-ai.io/v1",   # the one line that changes
    api_key=NUCLEUS_API_KEY,
)

client.chat.completions.create(
    model="nucleus://run_3Bz:train:0/sampler_weights/000240",
    messages=[{"role": "user", "content": "Triage this ticket"}],
)
200 OK
served
model
…/sampler_weights/000240
prompt_tokens
512
completion_tokens
128
latency
142 tok/s
Overview

Call your model the way you already call one

Change one line

Point your OpenAI or Anthropic client at Nucleus and keep the rest of your code.

Base model or your checkpoint

The model parameter takes a base model ID or the nucleus:// path of your fine-tuned weights, so one client serves both.

Pay for what runs

Serverless meters tokens and idle time costs nothing. A dedicated GPU bills by the second.

Capacity you can hold

Reserve a GPU for one to six months and the capacity is guaranteed.

National Neuroscience Institute logo
National University Hospital logo
Mandai Wildlife Group logo
SingHealth logo
Infocomm Media Development Authority logo
Institute for Adult Learning logo
Ministry of Education logo
Nanyang Polytechnic logo
Institute of Singapore Chartered Accountants logo
Ministry of Health logo
National Neuroscience Institute logo
National University Hospital logo
Mandai Wildlife Group logo
SingHealth logo
Infocomm Media Development Authority logo
Institute for Adult Learning logo
Ministry of Education logo
Nanyang Polytechnic logo
Institute of Singapore Chartered Accountants logo
Ministry of Health logo
National Neuroscience Institute logo
National University Hospital logo
Mandai Wildlife Group logo
SingHealth logo
Infocomm Media Development Authority logo
Institute for Adult Learning logo
Ministry of Education logo
Nanyang Polytechnic logo
Institute of Singapore Chartered Accountants logo
Ministry of Health logo
National Neuroscience Institute logo
National University Hospital logo
Mandai Wildlife Group logo
SingHealth logo
Infocomm Media Development Authority logo
Institute for Adult Learning logo
Ministry of Education logo
Nanyang Polytechnic logo
Institute of Singapore Chartered Accountants logo
Ministry of Health logo
Trusted by leading institutions
Product

Five ways in, one key

Point your OpenAI or Anthropic client at Nucleus and authenticate with your Nucleus key. The model parameter takes a base model ID or the nucleus:// path of your fine-tuned checkpoint. Both routes need a key with the infer scope.

Read the OpenAI-compatible reference
Results

Results from LLMs powered by Nucleus

$2.4K

daily fuel saved across the fleet

23

delays resolved without a call

Same day

from site reading to client report

6.2 hrs

average time to resolution

Workflows

Models behind a live feed

Fleet operations

47 trucks rerouted while they were still moving

$2.4Kdaily fuel saved across the fleet
23delays resolved without a call
Field engineering

Cable survey readings processed while the crew was still on site

Same dayfrom site reading to client report
9systems on one thread
Logistics

Every shipment two days past ETA, found before the customer called

Dailysweep of the tracking feed
2 dayspast ETA is the escalation line
At a glance

What the Serve column includes

Routes

  • OpenAI-compatible chat completions and completions at /v1
  • Anthropic-compatible messages and count_tokens at /anthropic
  • Token-level sampling on /v1/samplers
  • Streaming over server-sent events on completions, chat completions and messages

Models

  • A base model ID or a nucleus:// checkpoint path
  • Language, vision, embedding and reranking, image, video and audio groups
  • A fine-tuned model served at its base model's rate

Capacity

  • Serverless per token, idle costs nothing
  • Dedicated L40S, A100, H100, H200 and B200 by the second
  • Reserved one to six months, 15 to 25% below on-demand
  • Cold start free

Keys and metering

  • Keys carry scopes, and serving needs infer
  • Authorization Bearer everywhere, x-api-key accepted on the Anthropic route
  • The usage API reports inference tokens by day, project or base model
  • Count tokens before you send
PRICING

Two meters run the serving bill

Served tokens

from $0.02per 1M tokens

Input and output tokens cost the same. Dedicated GPUs from $1.99 per GPU-hour, billed by the second. Reserved from $1.49.

Pick your path

Pick your path

Private Endpoints

OpenAI and Anthropic compatible

Explore Private Endpoints

Serverless

Pay per token, idle costs nothing

Explore Serverless

Dedicated GPUs

L40S to B200, by the second

Explore Dedicated GPUs

Reserved capacity

Guaranteed terms, one to six months

Explore Reserved capacity

Compatible APIs

Docs

One key, two SDK families

Explore Compatible APIs

Change one line and call your model

Your OpenAI or Anthropic client works as it is. Pick the capacity that fits the traffic.