Models / Custom models

Custom AI model API: a base model, a persona and your own model id

A custom AI model API on one prepaid key. Pick a base model from the catalog, give it a persona, default settings and up to 5 fallbacks, and save it under a name you choose. From then on model: "support-bot" is a model id: Cursor, SillyTavern, LangChain, n8n, Claude Code and any OpenAI or Anthropic SDK call it unchanged. No training, no hosting, billed at the base model's price.

Create a custom model https://api.uplinkswitch.com/v1

Create a custom model, then call it · one PUT, one id

curl · define the model (admin key)
curl -X PUT https://api.uplinkswitch.com/v1/presets/support-bot \
  -H "Authorization: Bearer sk-uplink-live-...admin" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5-5",
    "models": ["gpt-6.1-sol","gemini-4-argon"],
    "params": {"temperature": 0.3, "max_tokens": 800},
    "system_prompt": "You are Ada, the support agent for Acme. Answer billing questions in two sentences.",
    "system_mode": "prepend",
    "description": "Billing support persona"
  }'
Python · OpenAI SDK, called by name
from openai import OpenAI

client = OpenAI(base_url="https://api.uplinkswitch.com/v1", api_key="sk-uplink-live-...")

res = client.chat.completions.create(
    model="support-bot",  # your custom model id; also @preset/support-bot
    messages=[{"role": "user", "content": "Why was I charged twice?"}],
)
print(res.model)  # the base or fallback model that answered
Python · Anthropic SDK, same id
import anthropic

client = anthropic.Anthropic(base_url="https://api.uplinkswitch.com/v1", api_key="sk-uplink-live-...")

msg = client.messages.create(
    model="support-bot",
    max_tokens=400,
    messages=[{"role": "user", "content": "Why was I charged twice?"}],
)
print(msg.content[0].text)
Claude Code · the custom id as the model
# Claude Code, Cursor, SillyTavern, LangChain, n8n: the model field takes the custom id.
export ANTHROPIC_BASE_URL="https://api.uplinkswitch.com/v1"
export ANTHROPIC_AUTH_TOKEN="sk-uplink-live-..."
export ANTHROPIC_MODEL="support-bot"

The same id works on /v1/chat/completions, /v1/responses and /v1/messages. The answer's model field and the x-uplink-model header name the model that answered; x-uplink-preset names the custom model. Writes need an admin key or the console; API keys call but cannot change.

What a custom model holds · up to 100 per organization, every change versioned

FieldWhat it is
Name1 to 64 characters: lower-case letters, digits, dots, dashes and underscores. It may not shadow a catalog model or one of your aliases.
Base modelAny model id from the live catalog, or one of your org’s aliases.
FallbacksUp to 5 models tried in order when every route of the one before failed before a byte.
Defaultstemperature, top_p, max_tokens, stop and the other request parameters. A value the request sends always wins.
System promptUp to 32 KB. Prepend puts it ahead of the caller’s system prompt; replace swaps the caller’s out.
ToolsTool declarations the model gets on every call; request tools of the same name replace them.
DescriptionA line for your team and for the model picker.

What it costs · the base model's price per million tokens, USD, read 2026-11-16

Base modelInputOutputDeveloper list, output
Claude Fable 5.2$4.00$20.00$40.00
Claude Fable 5.1$6.00$30.00$50.00
Claude Opus 5.5$2.716$9.70$20.00
Claude Sonnet 5.5$1.20$3.00$10.00
GPT-6.1 Sol$0.582$2.91$10.00
GPT-6 Sol$0.60$3.00$10.00
GPT-5.5$1.80$9.00$30.00
Gemini 4 Argon$0.60$3.00$10.00

A custom model adds nothing to the price: the model that answered bills at its own catalog rate, the base or the fallback that took over. Any of the chat models can be the base, uncensored builds included. The daily real-model check shows which models answered as themselves today.

Every way to name it · the bare name, the @ forms, or a preset field

"model": "support-bot"The bare name. Works wherever an app takes a model id.
"model": "@preset/support-bot"The explicit form; the @ prefix on its own also works.
"model": "deepseek-v4-pro-0813@preset/support-bot"The custom model’s prompt, defaults and fallbacks on another base model for this one request.
"preset": "support-bot"A field beside any model, for clients that keep the model field fixed.

GET /v1/models lists your custom models next to the catalog, so a model picker in Cursor, SillyTavern or n8n shows them by name. The same request shapes work in the OpenAI chat and Responses formats and the Anthropic Messages format.

Create your own AI model API without training · what changes, what stays

Most guides on how to create your own AI model API start with a dataset, a GPU and a serving stack. Most apps that want "their own model" need none of that. They need a model that answers as one persona, follows one set of rules, uses one temperature and one output cap, and keeps answering when a vendor has a bad hour. All of that lives in the request, not in the weights.

A custom model here moves those parts out of your code and onto your key. The system prompt is attached on every call, in prepend mode ahead of whatever the app sends, or in replace mode instead of it. The defaults apply when the request leaves a parameter out; a value the request sets always wins. The fallbacks answer in order when every route of the model before them fails before a byte. Change any of it in the console and every app calling the name gets the new behavior on its next request, with the old version kept in history.

What stays is the base model's knowledge and quality. A custom model built on Claude Fable 5.2 answers like it, at its price, under your name. If the job needs new weights, that is fine-tuning, and this is not it: no training runs here, and nothing you send teaches the model.

Common shapes: a support agent with the company's rules and a strict output cap; a SillyTavern character whose card and settings live on the key, so every front end gets the same persona; a coding model for Cursor or Claude Code with a frontier base and two cheaper fallbacks; an uncensored writing model built on an abliterated base with the house style in the prompt. Each is one PUT and one name.

A custom model keeps its own base model. On an auto router key every other request is routed, and a custom model called by name is not. The routing, fallbacks and presets page covers the request-level forms of the same features, and the SDK guide shows the base URL and key in Python, TypeScript, Go and Rust.

Custom AI model API questions

An API where the model id in your request is one you defined, not a stock id from a vendor. Here a custom model is a saved configuration on your account: a base model from the catalog, up to 5 fallbacks, default parameters, a system prompt and tool declarations under a name you choose. Any OpenAI or Anthropic SDK calls it by that name on the same base URL and key as every other model.

Yes, in the sense most apps need: a model that answers as your persona, with your rules, your settings and your fallback order, under your own id, in about a minute and with no training. If you need new weights, that is fine-tuning, which is a different product and not offered here. A custom model here changes what the base model is told and how it is called, not what it learned.

Not here. Every request bills at the base model’s live catalog price per token, and a custom model adds no fee on top. The key is prepaid from $10, with no subscription. The daily real-model check at /proof shows which models answered as themselves today.

The price of the model that answered, from its catalog row: the base model, or the fallback that took over. There is no per-model fee, no hosting charge and no minimum. The x-uplink-model response header names the model billed and x-uplink-preset names the custom model.

Anything that takes a base URL and a model id: Cursor, Cline, Roo Code, Claude Code, SillyTavern, Janitor-style front ends, LangChain, LlamaIndex, n8n, Zapier, and your own code on the OpenAI or Anthropic SDK. GET /v1/models lists your custom models next to the catalog, so model pickers show them without typing the name.

Yes. Set the base model to any uncensored or abliterated build in the catalog, add the persona and rules in the system prompt, and call it by name from SillyTavern or your app. The /uncensored page lists every such build with its price.

An admin key or a console session, on PUT /v1/presets/<name> or on the console’s Presets page. Plain API keys call custom models but cannot write them. An org holds up to 100, and every create, change and delete keeps the previous version in history.

The fallbacks answer in the order you listed them, each at its own price, and the response says which one did. Without fallbacks the request fails the way a direct call to that model would.

Get your key.

Prepaid from $10 or a monthly plan, 30-day price lock.

  • One key, every model
  • The SDK you already use
  • Prepaid, or a monthly plan
  • 30-day price lock on every top-up
  • Signed receipts for every call
Join on Telegram