meta-llama/llama-4-scout
327,680 context · $0.18/M input tokens · $0.59/M output tokens
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...
定價
按用量付費
無需預付費用，僅按實際使用量付費
試用模型
API 使用
使用以下程式碼範例整合我們的 API：
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="meta-llama/llama-4-scout",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)模型介紹
Meta-Llama llama-4-scout
meta-llama llama-4-scout
Why It Looks Great
- Large Language Model architecture for efficient processing
- 327680 context window for long document handling
- Competitive pricing at $0.1/$0.3 per million tokens
Key Features
- Context Window: 327680 tokens
- Max Output: 16384 tokens
- Vision: Supported
- Function Calling: Supported
Specifications
| Specification | Value |
|---|---|
| Provider | Meta-Llama |
| Model Type | Large Language Model (LLM) |
| Architecture | N/A |
| Context Window | 327680 tokens |
| Max Output | 16384 tokens |
| Input | Text |
| Output | Text |
| Vision | Supported |
| Function Calling | Supported |
Pricing
| Token Type | Cost per Million Tokens |
|---|---|
| Input | $0.1 |
| Output | $0.3 |
How to Use
- Write your prompt — describe the task, provide context, and specify desired output format.
- Submit — the model processes your request and returns the response.
API Integration
Base URL: https://llm.wavespeed.ai/v1 API Endpoint: chat/completions Model ID: meta-llama/llama-4-scout
API Usage
Python SDK
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://llm.wavespeed.ai/v1"
)
response = client.chat.completions.create(
model="meta-llama/llama-4-scout",
messages=[
{"role": "user", "content": "Hello!"}
]
)
print(response.choices[0].message.content)cURL
curl https://llm.wavespeed.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "meta-llama/llama-4-scout",
"messages": [{"role": "user", "content": "Hello!"}]
}'Notes
- Model: meta-llama/llama-4-scout
- Provider: Meta-Llama
資訊
支援功能
API 存取指南
Llama 4 Scout API
meta-llama/llama-4-scout
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...
輸入
$0.18 /M
輸出
$0.59 /M
上下文
328K
最大輸出
16K
Vision
支援
工具調用
支援
在 WaveSpeedAI 試用 Llama 4 Scout
透過我們的統一 API 接入 Llama 4 Scout — 相容 OpenAI、無冷啟動、透明計費。
關於 Llama 4 Scout 的常見問題
Llama 4 Scout API 多少錢?+
WaveSpeedAI 定價:輸入每百萬 token $0.18,輸出每百萬 token $0.59。Prompt 快取與批次處理分別計費,可顯著降低長上下文、高重複任務的實際成本。
Llama 4 Scout 的上下文視窗有多大?+
Llama 4 Scout 每次請求最多支援 328K 上下文 token,輸出最多 16K token。
Llama 4 Scout 是否相容 OpenAI?+
是的。WaveSpeedAI 透過 https://llm.wavespeed.ai/v1 的 OpenAI 相容端點提供 Llama 4 Scout。將官方 OpenAI SDK 的 base URL 指向該位址,使用 WaveSpeedAI 的 API Key 即可,無需其他程式碼變更。
如何開始使用 Llama 4 Scout?+
登入 WaveSpeedAI,在 Access Keys 建立 API Key,使用上方顯示的 model id 向 https://llm.wavespeed.ai/v1/chat/completions 發送請求。新帳號將獲得免費額度,用於試用 Llama 4 Scout。