Meta

Meta Llama 4 Scout

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 consoleGet an API key
Context window
1.3Mtokens
Max output
16Ktokens
Input
$0.10/ 1M
Output
$0.30/ 1M

Quick start

from openai import OpenAI

client = OpenAI(
    base_url="https://neurongate.net/v1",
    api_key="sk-ng-your-api-key",
)

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

Cost

Example requestTokensCost
Short prompt1K in$0.0001
Typical chat turn1K in · 500 out$0.00025
Document analysis10K in · 2K out$0.0016
Long context100K in · 10K out$0.013
Estimated cost per request$0.00025

Prices in USD. Billed per token actually used, from a balance prepaid in USDT, USDC, ETH or BTC.

Frequently asked questions

What is Meta Llama 4 Scout?

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...

How much does Meta Llama 4 Scout cost?

Meta Llama 4 Scout is priced at $0.1 per 1 million input tokens and $0.3 per 1 million output tokens when accessed via NeuronGate. You pay per token — no subscriptions required. Top up with crypto (USDT, USDC, ETH, BTC).

Does Meta Llama 4 Scout support streaming?

Yes, Meta Llama 4 Scout supports streaming responses via NeuronGate's API. Use the standard "stream": true parameter in your request.

What is the context window of Meta Llama 4 Scout?

Meta Llama 4 Scout has a context window of 1.3M tokens (~983K words). Maximum output is 16K tokens.

Does Meta Llama 4 Scout support function calling (tools)?

Yes, Meta Llama 4 Scout supports function calling / tool use via NeuronGate's standard API.

How do I use Meta Llama 4 Scout with NeuronGate?

Create a NeuronGate account, top up your balance with crypto, generate an API key, and use the model id meta-llama/llama-4-scout in your requests. NeuronGate uses the OpenAI-compatible API format — set your base URL to https://neurongate.net/v1.