Introduction

Quickstart

You need credit and an API key before making a request.

1. Create an account, confirm you are 18 or older, and add credit from Billing.
2. Create a key under API keys. Copy the secret when it appears. Arscelare cannot show it again.
3. Use https://api.arscelare.ai/v1 as the base URL in your client. Send the key as a bearer token.

curl

curl https://api.arscelare.ai/v1/chat/completions \
  -H "Authorization: Bearer $ARSCELARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"ars-1","messages":[{"role":"user","content":"Continue the scene."}]}'

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.ARSCELARE_API_KEY,
  baseURL: "https://api.arscelare.ai/v1",
});

const completion = await client.chat.completions.create({
  model: "ars-1",
  messages: [{ role: "user", content: "Continue the scene." }],
});
console.log(completion.choices[0].message.content);

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["ARSCELARE_API_KEY"],
    base_url="https://api.arscelare.ai/v1",
)

completion = client.chat.completions.create(
    model="ars-1",
    messages=[{"role": "user", "content": "Continue the scene."}],
)
print(completion.choices[0].message.content)

Model

Use ars-1 as the model ID in every request.

id

ars-1

name

Arscelare 1

context

65,536 tokens

max output

8,192 tokens

Pricing

Add credit in fixed USDC packs. You pay for the tokens each request uses. There is no subscription.

Credit packs

• 10 USDC
• 25 USDC
• 50 USDC
• 100 USDC

Token rates

input

2.50 USDC / MTok

cached input

0.60 USDC / MTok

output

5 USDC / MTok

The cached-input rate applies when the model server reports a cache hit. Reasoning tokens use the output rate.

Rate limits

Every account with credit has the same request and token limits:

• 50 RPM (requests / minute)
• 1,000,000 TPM (prompt + completion tokens / minute)

There is no daily cap. Requests above either limit return 429 rate_limit_error.

API reference

Set your client's base URL to https://api.arscelare.ai/v1.

Authentication

Send your API key in either form:

Authorization: Bearer <key>
# or
Authorization: Api-Key <key>

A missing, unknown, or revoked key returns 401 authentication_error.

Endpoints

• GET /v1/models. This public endpoint returns an OpenAI-compatible model list containing ars-1.
• POST /v1/chat/completions. This endpoint requires an active API key and sufficient balance. It supports messages, temperature, max_tokens / max_completion_tokens, stop, stream, top_p, seed, and stream_options. Tool calls, functions, and n values other than 1 are not supported.

Errors

{
  "error": {
    "message": "Human-readable description",
    "type": "<error_type>"
  }
}

• 400 invalid_request_error
• 401 authentication_error
• 402 insufficient_quota
• 429 rate_limit_error
• 502 server_error

Usage object

{
  "prompt_tokens": 0,
  "completion_tokens": 0,
  "total_tokens": 0,
  "prompt_tokens_details": { "cached_tokens": 0 },
  "completion_tokens_details": { "reasoning_tokens": 0 }
}

cached_tokens reports the prompt prefix reused by the model server and billed at the cached-input rate. completion_tokens includes reasoning tokens. When available, reasoning is returned as reasoning_content on the assistant message or streaming delta.