Question 1

What is Llama 4 Scout 17B 16E Instruct?

Accepted Answer

Llama 4 Scout 17B 16E Instruct 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 17B 16E Instruct cost?

Accepted Answer

On the Respan gateway, input starts at $0.10 per 1M tokens on DeepInfra, and output starts at $0.30 per 1M tokens on DeepInfra, after gateway discounts. Averaged across 3 providers, it costs $0.15 per 1M input tokens and $0.47 per 1M output tokens.

Question 3

Which providers serve Llama 4 Scout 17B 16E Instruct on Respan?

Accepted Answer

3 providers serve Llama 4 Scout 17B 16E Instruct: DeepInfra, Novita, and TogetherAI. TogetherAI requires your own provider API key (BYOK).

Question 4

What is Llama 4 Scout 17B 16E Instruct's context window?

Accepted Answer

Llama 4 Scout 17B 16E Instruct accepts up to 1.0M tokens of context on its largest provider route.

Question 5

How do I use Llama 4 Scout 17B 16E Instruct 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-17b-16e-instruct". 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 17B 16E Instruct?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was DeepInfra at 32 tokens per second, and the lowest response latency was 0.4 seconds on DeepInfra. Speed varies with request size and provider.

Provider	Context	Input	Output	Capabilities
DeepInfra`deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct`	328K	$0.10/M	$0.30/M
NovitaSave 10%`novita/meta-llama/llama-4-scout-17b-16e-instruct`	131K	$0.16/M	$0.53/M	—
TogetherAIBYOK only`together_ai/meta-llama/Llama-4-Scout-17B-16E-Instruct`	1.0M	$0.18/M	$0.59/M

Llama 4 Scout 17B 16E Instruct

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Apps