SERVE · SERVERLESS

Managed models, priced per token. Idle time costs nothing.

Every model in the catalogue serves at one USD rate per million tokens, input and output the same. A quiet hour bills nothing. A busy hour bills the tokens it served.

Served tokensMetered per million, input and output the same
live
$0.02from, per 1M tokens
$0.00idle hour
Language models
$0.15 to $6.50 / 1M
Fine-tuned models
Base rate
Standing per-model fee
None
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"}],
)

One rate per model.

Input and output tokens cost the same, in USD per million.

A quiet hour bills nothing.

You pay for the tokens you serve. Idle time costs nothing.

Your fine-tune at the base rate.

A fine-tuned model serves at the same per-token rate as its base model, with no standing per-model fee.

Your SDK already works.

Swap the base URL and your OpenAI or Anthropic client keeps the rest of its code.

HOW IT IS PRICED

What a serverless endpoint costs

Two things decide the bill: the model's rate and the tokens you serve.

PRICING

One rate per million tokens, by model group

Every base model carries a served-token price in USD per million, and input and output tokens cost the same. A fine-tuned model serves at its base model's rate. Media models meter the tokens of the encoded media: a megapixel image is roughly 4K tokens, a five-second 720p clip roughly 70K and a minute of audio roughly 3K.

Explore the models reference
Results

Results from LLMs powered by Nucleus

Daily

sweep of the tracking feed

Shipment Delay Management / Logistics

Same day

from site reading to client report

Real-Time Field Data Collection / Field engineering

23

delays resolved without a call

Intelligent Fleet Optimisation / Fleet operations

AT A GLANCE

Serverless, in four columns

Pricing

  • USD per million tokens
  • Input and output the same price
  • Fine-tuned models at the base rate
  • No standing per-model fee
  • Idle time costs nothing

Models

  • Language, 21
  • Vision, 7
  • Embedding and reranking, 6
  • Image generation, 4
  • Video generation, 3
  • Audio, 8
  • Media metered as tokens of the encoded media

Routes

  • OpenAI-compatible completions and chat completions
  • Anthropic-compatible messages
  • Samplers for token-level sampling
  • nucleus:// paths for your fine-tuned weights
  • The infer scope on serving routes

Usage

  • Served tokens reported for any date range
  • Grouped by day, project or model
  • Forecast before the bill and reconcile after it
PRICING

Know what you pay

Serverless runs on the served-tokens meter. Everything on this page is priced from the same catalogue the pricing page reads.

Served tokensMetered per million input and output tokens through the OpenAI- and Anthropic-compatible APIs.
from $0.02 / 1M
Language modelsTwenty-one bases, Nemotron 3.5 Lightning to Kimi K3.
$0.15 to $6.50 / 1M
Fine-tuned modelsServed at the same per-token rate as the base model.
Base rate
Idle timeNo standing per-model fee on serverless.
$0.00
Pick your path

The rest of Serve

Private Endpoints

OpenAI and Anthropic compatible

Explore Private Endpoints

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

Serve at per-token rates.

One rate per million tokens. Idle time costs nothing.