Question 1

What is Llama 4 Scout?

Accepted Answer

Llama 4 Scout is a model from Meta, released on 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 (text and image) and multilingual output (text and code) across 12 supported languages. Designed for assistant-style interaction and visual reasoning, Scout uses 16 experts per forward pass and features a context length of 10 million tokens, with a training corpus of ~40 trillion tokens. Built for high efficiency and local or commercial deployment, Llama 4 Scout incorporates early fusion for seamless modality integration. It is instruction-tuned for use in multilingual chat, captioning, and image understanding tasks. Released under the Llama 4 Community License, it was last trained on data up to August 2024 and launched publicly on April 5, 2025.

Question 2

How much does Llama 4 Scout cost?

Accepted Answer

On the Respan gateway, input starts at $0.10 per 1M tokens on OpenRouter, and output starts at $0.30 per 1M tokens on OpenRouter, after gateway discounts.

Question 3

Which providers serve Llama 4 Scout on Respan?

Accepted Answer

Llama 4 Scout is served by OpenRouter.

Question 4

What is Llama 4 Scout's context window?

Accepted Answer

Llama 4 Scout accepts up to 1.3M tokens of context.

Question 5

How do I use Llama 4 Scout with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "llama-4-scout". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Llama 4 Scout?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 26 tokens per second, and the lowest response latency was 0.7 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Llama 4 Scout score on benchmarks?

Accepted Answer

Llama 4 Scout has 3 published benchmark scores, including GPQA Diamond 57.2%, MMLU-Pro 74.3%, and SAGE 34.8%. Each score links to where it was published; the data is collected by llmmetric.com.

Llama 4 Scout

Providers

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Certified where it counts.

Benchmarks

Reasoning1

Knowledge1

Other1

Apps

Llama 4 Scout FAQ

Works with your entire stack

Built for AI agents.
Break less.
Ship more.