PlusAPI — API docs

An OpenAI-compatible endpoint for AEON, our own 27B model. If your code already talks to OpenAI, you change one line.

Quickstart

Get a key from pricing, then point any OpenAI SDK at our base URL.

from openai import OpenAI

client = OpenAI(
    base_url="https://plusapi.ai/v1",
    api_key="sk-plusapi-…",
)

r = client.chat.completions.create(
    model="aeon-27b",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(r.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://plusapi.ai/v1",
  apiKey: "sk-plusapi-…",
});

const r = await client.chat.completions.create({
  model: "aeon-27b",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(r.choices[0].message.content);

curl https://plusapi.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-plusapi-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "aeon-27b",
    "messages": [{"role":"user","content":"Hello!"}]
  }'

Authentication

Every request carries your key as a bearer token:

Authorization: Bearer sk-plusapi-…

Your key is your account. There is no login, no dashboard password, no identity attached — we store only a hash of it. Keep it safe: lose it and it can't be recovered, because we don't know who you are.

Base URL & model

Base URL	https://plusapi.ai/v1
Model	aeon-27b
Protocol	OpenAI Chat Completions (drop-in)

Only the AEON model is served, so the model field is optional — any value routes to it.

Chat completions

POST /v1/chat/completions — identical shape to OpenAI. Response includes a usage object with token counts (that's what you're billed on).

{
  "id": "chatcmpl-…",
  "choices": [{ "message": { "role": "assistant", "content": "…" },
                "finish_reason": "stop" }],
  "usage": { "prompt_tokens": 25, "completion_tokens": 42, "total_tokens": 67 }
}

Streaming

Set "stream": true for server-sent events, exactly like OpenAI. Token usage arrives in the final chunk.

stream = client.chat.completions.create(
    model="aeon-27b", stream=True,
    messages=[{"role":"user","content":"Tell me a story."}],
)
for chunk in stream:
    print(chunk.choices[0].delta.content or "", end="")

List models

curl https://plusapi.ai/v1/models \
  -H "Authorization: Bearer sk-plusapi-…"

Supported parameters

Parameter	Notes
messages	Required. Standard role/content array.
max_tokens	Output cap. Bounded by your plan's context.
temperature	0–2. Default 1.
top_p	Nucleus sampling.
stream	true for SSE.
stop	Stop sequences.

Rate limits

Each plan sets a max parallel requests and a requests-per-minute ceiling. Exceeding either returns 429; retry with backoff.

Plan	Parallel	Rate	Context	Monthly (fair use)
Free	1	40 / min	16K	100 requests
Pro	4	200 / min	32K	25M tokens
Business	8	400 / min	64K	45M tokens
Dedicated	~25	custom	custom	unmetered

Errors

Errors return an OpenAI-style JSON body: { "error": { "type", "message" } }.

Code	Meaning
401	Missing or invalid API key
402	Key expired, or free trial used up
403	Key disabled
429	Concurrency or rate limit hit
400	Malformed request or blocked content
502	Upstream model unavailable — retry

Billing

Pay with crypto (Bitcoin, Monero, USDT) or card. Subscriptions are a flat monthly plan with a generous monthly token allowance (fair use). No card is stored for crypto, and there are no chargebacks or freezes.

Requests that violate our Acceptable Use Policy — for example, content sexualizing minors — are blocked and return 400.