Llama 4 Scout
Access Llama 4 Scout through one API key. Meta's open-weight model with 512K context.
Meta's latest open-weight model. Strong performance on reasoning, coding, and instruction-following with competitive pricing.
No credit card required. Takes 30 seconds.
2,400+
Developers
1.2M+
API calls served
100+
Endpoints
$0.01
Per call
Yep, that's it.
Try it live
Send a message and see Llama 4 Scout respond in real time.
Maximum tokens in the response.
Real-time tokens
Context Window
512K tokens
Max Output
8K tokens
Input Price
$0.21 / 1M tokens
Output Price
$0.84 / 1M tokens
Strengths
Meta releases Llama 4 Scout's weights openly, so behavior is transparent and portable — useful for teams that value avoiding lock-in.
Handles up to 512,000 tokens per request, enough to load large documents, long histories, or substantial codebases in one call.
Performs well on reasoning, instruction-following, and coding for an open model, making it a capable general-purpose option.
At $0.21 per 1M input and $0.84 per 1M output tokens, it offers large-context capability at a price close to the cheapest closed models.
Quick start
Copy this snippet and start making calls with Llama 4 Scout.
const res = await fetch('https://api.yepapi.com/v1/ai/chat', {
method: 'POST',
headers: {
'x-api-key': 'YOUR_API_KEY',
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "meta-llama/llama-4-scout",
"messages": [
{
"role": "user",
"content": "Explain API gateways in 2 sentences."
}
],
"maxTokens": 256
}),
});
const { data } = await res.json();
console.log(data.message.content);Why use Llama 4 Scout through YepAPI?
Llama 4 Scout API — pricing, context window & access
Llama 4 Scout is Meta's latest open-weight model, combining strong general capability with a large 512,000-token context window. It returns up to 8,192 output tokens per response.
Through YepAPI you call Llama 4 Scout on an OpenAI-compatible endpoint with one key — the same key that also reaches GPT-4o, Claude, Gemini, DeepSeek, and the SEO, SERP and scraping endpoints.
What is Llama 4 Scout?
Llama 4 Scout is part of Meta's Llama 4 generation of open-weight models. Its distinguishing feature is a 512,000-token context window paired with solid reasoning, coding, and instruction-following — a lot of capability for a model whose weights are openly released. Because it's open-weight, its behavior is transparent and portable, which appeals to teams wary of being locked into a single closed provider. It's positioned as a competitive general-purpose model for those who want frontier-class context length without frontier-class pricing.
Build with Llama 4 Scout via YepAPI
YepAPI exposes Llama 4 Scout through the OpenAI-compatible /v1/ai/chat endpoint, so you call Meta's model using the chat-completions format and the model string llama-4-scout. Switching between Llama 4 Scout and a closed model like GPT-4o, Claude, or Gemini is a single string change — handy for benchmarking open against closed on your own tasks. Your one key also covers search and scraping endpoints, so everything runs on the same account.
Llama 4 Scout API pricing — $0.21 / 1M input, $0.84 / 1M output
Llama 4 Scout costs $0.21 per 1M input tokens and $0.84 per 1M output tokens through YepAPI. That puts an open-weight model with a 512K context window at roughly the price of the cheapest closed small models — a strong value for long-context work. It's well-suited to jobs that combine large inputs with high volume, where both context length and per-token cost matter. You pay only for tokens used, with no minimums.
Llama 4 Scout for long-context, open-model workloads
Scout's 512K window lets you feed it big documents, extended conversation histories, or sizeable codebases without splitting them up. For teams that prefer an open-weight model — for transparency, portability, or to avoid single-vendor lock-in — it offers that option while staying competitive on reasoning and coding. Run it as your default for long-context tasks and escalate to a closed flagship only when a job genuinely needs more.
Try Llama 4 Scout free
New YepAPI accounts get $5 in free credit, no card required. At these rates that's plenty to test Llama 4 Scout's 512K context on a real document or codebase. Sign up, grab your key, and start calling Llama 4 Scout in minutes.
Start generating in 30 seconds
$5 free credit on signup. No credit card required. Pay per call.
What developers say
“Switched from SerpAPI and cut our SERP costs by 80%. Same data quality, way simpler billing.”
“One API key for AI models, SERP data, and web scraping. Saved us from managing 4 separate providers.”
“The $5 free credit let us prototype our entire rank tracking feature before committing. No other API does that.”
Frequently asked questions
Meta's latest open-weight model. Strong performance on reasoning, coding, and instruction-following with competitive pricing.
Input tokens cost $0.21 per 1M tokens and output tokens cost $0.84 per 1M tokens through YepAPI. No monthly minimums — you only pay for what you use.
Sign up for a free API key, then send requests to the /v1/ai/chat endpoint.
Llama 4 Scout supports a 512K token context window with up to 8K output tokens per request.
Ready to use Llama 4 Scout?
$5 free credit on signup. No credit card required. Pay per call.
Explore more models
Llama 4 Maverick
MetaAccess Llama 4 Maverick through one API key. Meta's most capable open-weight model.
GPT-4o Mini
OpenAIAccess GPT-4o Mini through one API key. Fast, cheap, and OpenAI-compatible.
GPT-4o
OpenAIAccess GPT-4o through one API key. Flagship reasoning and multimodal capabilities.