We use cookies. Cookies and browser storage keep you signed in and remember your preferences. With your permission we also measure how the site is used. You can any time. See our cookie policy.
Meta: Llama 4 Scout
meta-llama/llama-4-scoutTry Meta: Llama 4 Scout now
Runs on your balance at the prices above. New accounts start with free usage.
One API. Every model.
Session cost $0.00
Settings
Advanced parameters
Meta: Llama 4 Scout at a glance
- Input price is 78% lower than the median of 434 Text models.
- Context window of 1,310,720 tokens, enough for long documents and multi-turn conversations.
- Supports tool (function) calling for agents and integrations.
- Supports structured JSON output with a schema.
- Accepts images as input (vision).
- A typical request (1,000 input / 500 output tokens) costs about $0.000875.
About Meta: Llama 4 Scout
Meta: Llama 4 Scout is a language model developed by Meta. It is a mixture-of-experts model that activates 17 billion parameters out of a total of 109 billion, and it is published under the name Llama 4 Scout 17B Instruct (16E). It sits in the text category on api14, and its knowledge cutoff is 2024-08-31.
The model accepts text and images as input and returns text. Its context window is 1,310,720 tokens, which is large enough to hold very long documents, codebases or multi-turn histories in a single request, and the maximum output length is 16,384 tokens. Native multimodal input means you can send images alongside text prompts, so tasks that mix a screenshot, diagram or photo with written instructions are supported directly rather than through a separate pipeline.
Those capabilities point to a few practical uses. Long-context work such as summarising or querying lengthy reports, contracts or transcripts fits the large window well. Because images are accepted as input, document understanding, chart and screenshot analysis, and visual question answering are reasonable fits. Tool calling and structured outputs make it suitable for agents and pipelines that need the model to return data in a fixed shape or invoke external functions, and the mixture-of-experts design keeps the active parameter count at 17 billion, which is relevant if you care about serving efficiency rather than raw scale.
You call it through api14's OpenAI-compatible API using the model id "meta-llama/llama-4-scout". The supported request parameters are frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k and top_p. That set covers sampling controls, deterministic runs via seed, stop sequences, JSON or schema-constrained responses through response_format and structured_outputs, and function calling through tools and tool_choice.
Two limits are worth noting before you commit. Output is capped at 16,384 tokens per response, so work that needs a very long single completion has to be split across calls. The knowledge cutoff is 2024-08-31, so questions about events after that date depend on what you supply in the prompt or through tools. If your task is purely text and does not need the large context window or image input, a smaller model may be a simpler choice.
How to call the Meta: Llama 4 Scout API
- Create an API key in your dashboard.
- Install the official openai SDK for your language.
- Set baseURL to https://api14.com/api/v1 and model to "meta-llama/llama-4-scout".
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api14.com/api/v1",
apiKey: process.env.API14_API_KEY,
});
const result = await client.chat.completions.create({
"model": "meta-llama/llama-4-scout",
"messages": [
{
"role": "user",
"content": "Explain vector databases in two sentences."
}
]
});
console.log(result.choices[0].message.content);
Supported parameters
frequency_penaltylogit_biasmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_pSpecifications
- Context length
- 1,310,720
- Max output
- 16,384
- Input
- text, image
- Output
- text
- Knowledge cutoff
- 2024-08-31
Requests on api14 · last 7 days
Meta: Llama 4 Scout: frequently asked questions
- How much does the Meta: Llama 4 Scout API cost?
- Meta: Llama 4 Scout costs Input $0.35 / 1M tokens. It is charged from your USD balance only for successful requests; failed requests are free.
- What is the context window of Meta: Llama 4 Scout?
- Meta: Llama 4 Scout reads up to 1,310,720 tokens per request: prompt, history and documents together. It writes up to 16,384 output tokens per response.
- What can Meta: Llama 4 Scout do?
- Meta: Llama 4 Scout accepts text, image and returns text. It supports tool calling, structured JSON output.
- How do I call Meta: Llama 4 Scout from my code?
- Point any OpenAI SDK at https://api14.com/api/v1 and set the model to "meta-llama/llama-4-scout". No other code changes. Copy a ready example from the code panel on this page.
- What are alternatives to Meta: Llama 4 Scout?
- Comparable Text models at a similar price: NVIDIA: Nemotron 3.5 Content Safety, StepFun: Step 3.5 Flash, Mistral: Ministral 3 14B 2512. Each runs through the same API key, so switching is one string.
Meta: Llama 4 Scout community
New topicThis community has no topics yet. Open the first one about Meta: Llama 4 Scout.