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
available
Cheapest
IBM watsonx.ai
$1.80/1M tokens
IBM watsonx.ai
Sorted by total cost (input + output per 1M tokens). Click a row to view provider details.
| Provider | Pricing (per 1M) | Rate Limits | Regions | Health | Latency |
|---|---|---|---|---|---|
In: $0.60Out: $1.20 | 50 RPM / 200K TPM | us-south-1eu-de-1eu-gb-1 | Healthy | 0ms |
Use this model via IBM watsonx.ai with an OpenAI-compatible 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);Using IBM watsonx.ai API • OpenAI-compatible SDK