AIVory Smart Inference · Llama

Open Weight

Llama 4 Scout - the right MoE for most jobs.

Meta's efficient MoE model. 109B total, 17B active per token. Better quality than Llama 3.3 70B, lower cost than Maverick. The middle ground.

Start using Llama 4 Scout See pricing

At a glance

Llama 4 Scout via Smart Inference.

Routed to the cheapest live provider on every request. Same model, lower bill.

109B

Parameters

MoE (17B active)

128K

Context window

tokens per request

—

Cheapest input price

per 1M tokens via Smart Inference

—%

Cheaper

vs the priciest endpoint for the same model

Pricing

Llama 4 Scout: price comparison.

Our cheapest routed price vs what you'd pay elsewhere.

Prices in USD per 1M input tokens · updated live from the router

Quick start

Use Llama 4 Scout in three lines.

OpenAI-compatible. Swap your base_url, keep everything else.

from openai import OpenAI

client = OpenAI(
    base_url="https://smart.aivory.net/v1",
    api_key="sk-aivory-...",
)

resp = client.chat.completions.create(
    model="llama-4-scout",
    messages=[{"role": "user", "content": "Ship it."}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://smart.aivory.net/v1",
  apiKey: process.env.AIVORY_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "llama-4-scout",
  messages: [{ role: "user", content: "Ship it." }],
});

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

curl https://smart.aivory.net/v1/chat/completions \
  -H "Authorization: Bearer $AIVORY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-4-scout",
    "messages": [{"role": "user", "content": "Ship it."}]
  }'

That's the whole migration. Get early access and try it →

Use cases

What Llama 4 Scout is great at.

Mid-Tier Assistant Workloads

When Llama 3.3 70B isn't quite good enough and Maverick is overkill. Scout sits between them on both quality and cost. Use it for customer support, internal tools, and product assistants.
Structured Output and JSON Generation

Scout follows system prompt formatting instructions reliably. Ask for JSON, markdown tables, or XML and it stays on format. Good for API backends that need predictable output schemas.
Multilingual Chat

The Llama 4 family has better multilingual coverage than Llama 3.3. Scout handles Spanish, French, German, Portuguese, and several Asian languages without needing a language-specific model.

FAQ

Common questions.

What does Llama 4 Scout cost on AIVory?

Scout is cheaper than Maverick but more expensive than Llama 3.3 70B. The exact rate depends on the provider the router picks. Check the live table above for current pricing.

Scout vs Maverick - when does Maverick justify the extra cost?

Maverick is stronger on complex reasoning, multimodal (image) tasks, and very long outputs. Scout handles most text-only tasks at similar quality. Default to Scout, switch to Maverick when you see quality gaps.

How does Scout compare to Qwen 3 235B?

Qwen 3 235B has more total parameters and scores higher on frontier benchmarks. Scout is cheaper and faster because it activates fewer parameters per token. For general assistant work, Scout is usually sufficient.

What's the license?

Meta's Llama 4 Community License. Same terms as Maverick: commercial use allowed, no royalties for apps under 700M MAU.

Explore

More models.

DeepSeek V3.2 DeepSeek · 671B · 160K context View pricing → DeepSeek V4 Flash DeepSeek · MoE · 128K context View pricing → Gemma 2 9B Gemma · 9B · 8K context View pricing → Gemma 4 31B Gemma · 31B · 128K context View pricing → All Models Browse the full catalogue with live pricing View all → Smart Inference AI inference routing · cheapest provider per request Learn more → GPU Marketplace Spot GPUs from $0.10/hr · H100, H200, RTX 4090 Compare prices →

Start using Llama 4 Scout. Today.

Swap your base_url, keep shipping.

The router is live. Credits from $10, no subscription, no commitment.

Get early access Read the docs