ibm-granite

IBM: Granite 4.1 8B

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

Context
131k tokens
Input / 1M tokens
$0.05
Output / 1M tokens
$0.10
Benchmark

Pricing

Input tokens$0.05 per 1M tokens
Output tokens$0.10 per 1M tokens
Cache read$0.05 per 1M tokens

Technical details

Model IDibm-granite/granite-4.1-8b
Context window131k tokens
Input modalitiestext
Output modalitiestext
TokenizerOther
Max output tokens131,072

Use with MegaBrain

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://getmegabrain.com/api/gateway/v1',
  apiKey: process.env.MEGABRAIN_API_KEY,
})

const response = await client.chat.completions.create({
  model: 'ibm-granite/granite-4.1-8b',
  messages: [{ role: 'user', content: 'Hello!' }],
})

Ready to use IBM: Granite 4.1 8B?

Get an API key and start making requests in minutes.

Get an API key