Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model from 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, it is instruction-tuned for multilingual chat, captioning, and image understanding.
$0.24
$0.96
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Daily usage of this model on NagaAI.
Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model from 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.
On NagaAI, Llama 4 Scout 17B 16E Instruct costs $0.24 per 1M input tokens and $0.96 per 1M output tokens. You pay only for what you use, with no subscription.
Llama 4 Scout 17B 16E Instruct reads up to 327.7k tokens in one request, counting the prompt and the answer together.
Yes. Llama 4 Scout 17B 16E Instruct can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Muse WonderMeta LlamaMuse Spark OpenMeta LlamaMuse Glimmer 30BMeta LlamaLlama 3.2 11B Vision InstructMeta Llama$0.10 / $0.10 per 1MLlama 3.2 3B InstructMeta LlamaLlama 3.2 1B InstructMeta LlamaNot enough throughput data
Not enough TTFT data