Private endpoints your SDK already speaks
Swap the base URL in your OpenAI or Anthropic client. The rest of your code stays the same, and every model you train serves behind its own endpoint, with keys, usage metering and scaling behind it.
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"}],
)One line changes.
Point your OpenAI or Anthropic client at a Nucleus base URL and keep the rest of your code.
Your own endpoint.
Every model you train serves behind its own endpoint, isolated to your account.
Scales with traffic.
Serving scales with your usage, and Nucleus runs the servers.
Every token accounted for.
The usage API reports served tokens for any date range, grouped by day, project or model.
Two routes, one key, everything behind it
Point any OpenAI client at https://api.nucleus-ai.io/v1 and authenticate with your Nucleus key. The model parameter takes a base model ID or the nucleus:// path of your fine-tuned weights, so the same client serves both. Chat completions renders your messages with the model's chat template on the server, and stream: true returns tokens as they are generated.
Results from LLMs powered by Nucleus
monthly revenue misattributed, found
trucks rerouted while they were still moving
downtime prevented this month
from site reading to client report
Three workflows served this way
Cable survey readings processed while the crew was still on site.
Every incident past its four-hour SLA, escalated by name.
47 trucks rerouted while they were still moving.
Private Endpoints at a glance
Routes
- Chat completions, POST /v1/chat/completions
- Completions, POST /v1/completions
- Messages, POST /anthropic/v1/messages
- Count tokens, POST /anthropic/v1/messages/count_tokens
- Streaming over text/event-stream on every route
- Reasoning controls: reasoning_effort, separate_reasoning; thinking, output_config.effort
- Prompt caching and citations are unsupported on the Anthropic route
Models
- Any base model from the catalogue: 25 open models across language, vision, image, video and audio
- Your fine-tuned checkpoints, by nucleus:// path
- A fine-tuned model serves at its base model's per-token rate
- Base model IDs and paths in the same model parameter
Keys and access
- Scopes read, train, infer, admin
- Project binding, so a key sees one project's resources
- nk_live_ production and nk_test_ sandbox prefixes
- Rotation with two keys valid at once
- GET /v1/auth/verify to see what a key can do
- Rate limits per key, reported in X-RateLimit headers
Operations
- Usage by day, project or model, GET /v1/usage
- Job events over SSE, resumable with after
- Audit log by UTC day, GET /v1/audit-log
- Automatic scaling with usage
- SSL, firewall and DDoS protection built in
- Serverless, dedicated or reserved capacity
Served tokens
Served tokens
Calls to your private endpoints are metered per million input and output tokens, through the OpenAI- and Anthropic-compatible APIs. Input and output tokens cost the same. A fine-tuned model is served at the same per-token rate as its base model. There is no premium and no standing per-model fee on serverless.
The three ways to run an endpoint
Serverless
Pay per token, idle costs nothing
Dedicated GPUs
L40S to B200, by the second
Reserved capacity
Guaranteed terms, one to six months
Compatible APIs
DocsOne key, two SDK families
Read next
Use the OpenAI SDK
Point any OpenAI client at Nucleus and chat with your fine-tuned model without changing your code.
Use the Anthropic SDK and Claude Code
Point the Anthropic SDK or Claude Code at a Nucleus-served model with a base URL change.
HDB Resale Price Dashboard enables real-time analysis of Singapore housing market data
A smart dashboard for querying and visualising millions of HDB resale data points in real time.
Ready to change one line?
Point your OpenAI or Anthropic client at a Nucleus endpoint today, or talk to sales about dedicated and reserved capacity.