Models / Llama 4 Scout

Llama 4 Scout

Llama 4 Community

Meta's efficient MoE model. 109B total with 17B active parameters and 10M context window.

meta/llama-4-scout
Context Window
524K
Max Output
33K
Providers
2
Released
2025-04

Capabilities

chatcodevisiontoolsstreaming

Pricing by Provider

ProviderInput $/1MOutput $/1MLatency p50Latency p95Status
deepinfra$0.15$0.50380ms1000ms
together$0.18$0.59350ms900ms

Quick Start

Python
import magicrouter

mr = magicrouter.Client(
    provider_keys={"deepinfra": "your-api-key"}
)

response = mr.chat(
    "meta/llama-4-scout",
    "Your prompt here"
)
print(response.choices[0].message.content)
TypeScript
import { MagicRouter } from "magicrouter";

const mr = new MagicRouter({
  providerKeys: { deepinfra: "your-api-key" }
});

const response = await mr.chat({
  model: "meta/llama-4-scout",
  messages: [{ role: "user", content: "Your prompt here" }]
});
console.log(response.choices[0].message.content);
cURL
curl https://api.deepinfra.com/v1/openai/chat/completions \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-4-Scout-17B-16E-Instruct",
    "messages": [{"role": "user", "content": "Your prompt here"}]
  }'

Use this model

Sign up for free and test Llama 4 Scout in the playground

Get Started
Llama 4 Scout — MagicRouter