Granite 4.2 8B

IbmMCP Tool CallReasoning

ibm/granite-4.2-8bOpen Weights

Reasoning model for deliberate analysis, multi-step problem solving, and tool use

Benchmark Pricing$0.10 / 1M in$0.15 / 1M out$0.05 cache read

Context: 131,072 tokens•Max Output: 117,964 tokens•Released: 2026-08-25

TECHNICAL SPECIFICATIONS

Context Window131,072131.1K tokens

Max Output117,964118K tokens

LicenseOpen SourceSelf-hostable

Input Modalities

Text

Function / Tool CallingSupported (MCP Ready)

Structured OutputsGuaranteed Schema

MODEL CONTEXT PROTOCOL (MCP) READINESS

✓ Granite 4.2 8B natively supports OpenAI / Anthropic format tool calling and is fully compatible with MCP servers and agent loops.

MCP Context Window Recommendations

With a context capacity of 131,072 tokens, this model can handle moderately large MCP tool definitions and multi-turn conversation logs comfortably.

API CALL INVOCATION EXAMPLE

// Example: Calling Granite 4.2 8B via OpenAI SDK
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.IBM_API_KEY,
});

const response = await client.chat.completions.create({
  model: "ibm/granite-4.2-8b",
  messages: [{ role: "user", content: "Hello! Can you inspect MCP tools?" }],
});

console.log(response.choices[0].message.content);