Skip to content
OpenKey

Llama 4 Scout

Meta AIReleased Apr 5, 2025

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

Try in playground
Context window
10M tokens
Max output
16K tokens
Input
text, image
Output
text
Tokenizer
Llama4
Knowledge cutoff
Aug 31, 2024
Released
Apr 5, 2025

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.100$0.0030$0.103
Output$0.300$0.0090$0.309

Benchmarks

Artificial Analysis

Intelligence index
10
Coding index
8.2
Agentic index
1.1

Design Arena

CategoryEloWin rateRank
Codemodels83926.6%#106
Data vizmodels94039.3%#96
Game devmodels83827.4%#105
UI componentsmodels82425.5%#100
Websitesmodels79322.7%#112

Head-to-head preference voting. How we filter and rank

Supported parameters

  • frequency_penalty
  • logit_bias
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model meta-llama/llama-4-scout.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/llama-4-scout",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="meta-llama/llama-4-scout",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "meta-llama/llama-4-scout",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Llama 4 Scout cost via API?
Through OpenKey, Llama 4 Scout costs $0.103 per 1M input tokens and $0.309 per 1M output tokens. That is the provider price ($0.100 / $0.300) plus a flat 3% fee — nothing else.
What is Llama 4 Scout's context window?
Llama 4 Scout accepts up to 10M tokens of context and returns up to 16K tokens per request.
Is Llama 4 Scout OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "meta-llama/llama-4-scout" using any OpenAI SDK — only the base URL and API key change.
What inputs does Llama 4 Scout support?
Llama 4 Scout accepts text, image input and produces text output. Its knowledge cutoff is Aug 31, 2024.

More from Meta AI

All Meta AI models →