Meta's efficient MoE model with 17B active parameters (109B total, 16 experts). Supports up to 10M token context — the longest of any production model. Strong performance on reasoning and multilingual tasks.
10.0M tokens
5
可用
价格最低
Deep Infra
$0.24/1M tokens
速度最快
Groq
95ms TTFT
Cerebras, Deep Infra, Groq, Replicate, Together AI
按每百万输入与输出 token 的总成本排序。选择一行可查看提供商详情。
| 提供商 | 价格(每百万) | 速率限制 | 区域 | 状态 | 延迟 |
|---|---|---|---|---|---|
输入: $0.06输出: $0.18 | 600 RPM / 1.0M TPM | us-east-1eu-west-1 | 正常 | 0ms | |
输入: $0.18输出: $0.18 | 600 RPM / 1.0M TPM | us-east-1us-west-2 | 正常 | 0ms | |
输入: $0.11输出: $0.34 | 30 RPM / 100K TPM | us-east-1eu-west-1 | 正常 | 95ms | |
输入: $0.15输出: $0.40 | 300 RPM / 500K TPM | us-east-1us-west-2 | 正常 | 0ms | |
输入: $0.60输出: $0.60 | 30 RPM / 60K TPM | us-east-1 | 正常 | 0ms |
通过 Deep Infra 使用此模型,兼容 OpenAI SDK。
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.deepinfra.com/v1/openai",
apiKey: process.env.DEEPINFRA_API_KEY,
});
const response = await client.chat.completions.create({
model: "meta-llama/Llama-4-Scout-17B-16E-Instruct",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);使用 Deep Infra API · 兼容 OpenAI SDK