alphaneural/auto

Router2M contextVisionTools

Routes each request to the cheapest model that can handle it — one that sees images if you send one, calls tools if you send tools, and fits your conversation — and moves up to a stronger model if that one fails. No fixed price: you pay for whichever models ran, at their listed prices, capped by max_spend (default $0.10 per request). Without a verify schema it escalates on errors and refusals only, not on answer quality.

Not one model but a rule for choosing one: each request starts on the cheapest capable model and moves up only when it has to, under a spend ceiling you set. Every reply carries a receipt naming the model that answered and what it cost.

alphaneural/auto

Call it from your code

Any OpenAI client works: point it at backend.alfnrl.io/v1 and send alphaneural/auto as the model. Add an X-Thread-Id header to keep a conversation going across models; the quickstart shows it.

Checking whether you are signed in…

Details

Model id: alphaneural/auto
Vendor: alphaneural
Reached: Routes each request to one of the models in this catalogue
Context window: 2,000,000 tokens
Max output: Not reported
Input: text, image
Output: text
Capabilities: Vision, Tools

Prices are what AlphaNeural AI bills, in USD, and can change when the upstream provider changes theirs. The catalogue is refreshed from the gateway every few minutes.

curl https://backend.alfnrl.io/v1/chat/completions \
  -H "Authorization: Bearer $ALPHANEURAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "alphaneural/auto",
    "max_spend": 0.1,
    "messages": [{"role": "user", "content": "Explain what a context window is, in two sentences."}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://backend.alfnrl.io/v1",
    api_key=os.environ["ALPHANEURAL_API_KEY"],
)

reply = client.chat.completions.create(
    model="alphaneural/auto",
    messages=[{"role": "user", "content": "Explain what a context window is, in two sentences."}],
    # A ceiling on what this request may bill, whichever models answer.
    extra_body={"max_spend": 0.1},
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://backend.alfnrl.io/v1",
  apiKey: process.env.ALPHANEURAL_API_KEY,
});

const reply = await client.chat.completions.create({
  model: "alphaneural/auto",
  messages: [{ role: "user", content: "Explain what a context window is, in two sentences." }],
  // A ceiling on what this request may bill, whichever models answer.
  // @ts-expect-error max_spend is an AlphaNeural extension.
  max_spend: 0.1,
});
console.log(reply.choices[0].message.content);