Meta's efficient open-weight model with 8 billion parameters from the Llama 3.1 family. Optimized for instruction following with strong performance on general tasks, coding, and multilingual benchmarks. Ideal for cost-effective deployment and edge inference scenarios.
131K tokens
2
可用
价格最低
Modal
$0.40/1M tokens
Modal, Scaleway
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: $0.20输出: $0.20 | 120 RPM / 400K TPM | us-east-1us-west-2 | 正常 | 0ms | |
输入: $0.30输出: $0.30 | 60 RPM / 200K TPM | eu-west-1 | 正常 | 0ms |
通过 Modal 使用此模型,兼容 OpenAI SDK。
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.modal.com/v1",
apiKey: process.env.MODAL_API_KEY,
});
const response = await client.chat.completions.create({
model: "meta-llama/Llama-3.1-8B-Instruct",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);使用 Modal API · 兼容 OpenAI SDK