Quick start

An OpenAI-compatible endpoint. Point an existing program at the base URL below, change the key, and nothing else has to move.

Base URL and authentication

https://api.aifromu.com/v1

Send your key as a bearer token in the Authorization header. A key is shown once when it is issued; rotate a lost one from the dashboard.

Your first request

Choose a plan — Buy a plan and open the dashboard; your API key is issued there and shown once.
Point at the base URL — Set the base URL in your client to this deployment and send the key as a bearer token.
Call a model — Name astra, sol-6.1, sol-6, terra or luna-6 as the model and send the request you already send.

curl https://api.aifromu.com/v1/models \
  -H "Authorization: Bearer $AI_FROM_U_API_KEY"

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aifromu.com/v1",
    api_key="YOUR_AI_FROM_U_API_KEY",
)

response = client.chat.completions.create(
    model="terra",
    messages=[
        {"role": "user", "content": "Hello from AI From U"}
    ],
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.aifromu.com/v1",
  apiKey: process.env.AI_FROM_U_API_KEY,
});

const response = await client.chat.completions.create({
  model: "terra",
  messages: [{ role: "user", content: "Hello from AI From U" }],
});

console.log(response.choices[0].message.content);

Model aliases

MODEL	GENERATION	BEST FOR
astra	GPT-6	Frontier reasoning on a 1M-token window, for the hardest work of all.
sol-6.1	GPT-6.1	Sol's GPT-6.1 model, the newest in the family, at 1.1 AI credits per input token.
sol-6	GPT-6	The GPT-6 generation of Sol, at 1.1 AI credits per input token.
terra	GPT-6.1	Fast, efficient everyday work — agents, tools, coding, computer use and visual tasks.
luna-6	GPT-6	The GPT-6 generation of Luna, at the lowest rates published here.

sol and luna still work as model names for existing integrations: they now run sol-6.1 and luna-6, billed at those models' rates. Requests that name GPT-5.6 Terra are served by terra, which runs GPT-6.1.

The five models · Which model should I use?

How credits are counted

Each token is multiplied by its model's factor — input, cache read, cache write and output are all published in the tables here. The factor is 5.5 on Astra, 1.1 on Sol 6.1 and Sol 6, 0.55 on Terra, and 0.055 on Luna 6; input and cache writes count the whole factor, a cache read counts half of it, and output and reasoning count 5× it.

Short context

MODEL	INPUT	CACHE READ	CACHE WRITE	OUTPUT + REASONING
astra	5.5	2.75	5.5	27.5
sol-6.1	1.1	0.55	1.1	5.5
sol-6	1.1	0.55	1.1	5.5
terra	0.55	0.275	0.55	2.75
luna-6	0.055	0.0275	0.055	0.275

Long context

MODEL	INPUT	CACHE READ	CACHE WRITE	OUTPUT + REASONING
astra	5.5	2.75	5.5	27.5
sol-6.1	1.1	0.55	1.1	5.5
sol-6	1.1	0.55	1.1	5.5
terra	0.55	0.275	0.55	2.75
luna-6	0.055	0.0275	0.055	0.275

A request with more than 272,000 input tokens converts at the long-context rate. Plans and pricing

Errors and limits

A request past your remaining credits is refused with 429 and nothing is charged. A 429 that carries a Retry-After header means the model is at capacity for a moment: wait that many seconds, then send the request again; it was not charged either. A key that has expired or been rotated answers 401.

Long generations should set stream: true — a non-streaming request running longer than about 100 seconds is cut by the edge before it returns.