IBM's largest dense decoder-only 30B parameter language model from the Granite 4.1 family. Trained on approximately 15T tokens with long-context extension up to 512K tokens. Supports tool calling, RAG, code generation, multilingual tasks across 12 languages. Released under Apache 2.0.
524K tokens
1
可用
价格最低
IBM watsonx.ai
$1.80/1M tokens
IBM watsonx.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: $0.60输出: $1.20 | 50 RPM / 200K TPM | us-south-1eu-de-1eu-gb-1 | 正常 | 0ms |
通过 IBM watsonx.ai 使用此模型,兼容 OpenAI SDK。
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.ibm-watsonx.com/v1",
apiKey: process.env.IBM_WATSONX_API_KEY,
});
const response = await client.chat.completions.create({
model: "ibm/granite-4-1-30b-instruct",
messages: [
{ role: "user", content: "Hello!" }
],
});
console.log(response.choices[0].message.content);使用 IBM watsonx.ai API · 兼容 OpenAI SDK