Enterprise DNAEnterprise DNA
LModelsLong context
I

Granite 4.2 8B

by Ibm Granite

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It s

G4

Models

Granite 4.2 8B

Added 3 Sept 2026

#ibm-granite

Overview

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It supports full, low-effort,...

How to use / API access

Call via OpenRouter with model id `ibm-granite/granite-4.2-8b`.

  • openrouter · ibm-granite/granite-4.2-8b Docs

OpenRouter id: ibm-granite/granite-4.2-8b

Benchmarks

  • Intelligence Index (artificial-analysis): 11.1 index
  • Coding Index (artificial-analysis): 22.4 index
  • Agentic Index (artificial-analysis): 1.3 index

Notes

Granite 4.2 8B is listed in the EDNA Models directory from the OpenRouter catalogue.

Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

USAGE / OPENROUTER

How much Granite 4.2 8B is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
6.2B ▼36.1%
Requests, last 7 days
1.2M
Tool calls, last 7 days
105K
Intelligence score
11.1
Average cost per request
3.9¢
Price per million tokens
$0.06 in · $0.25 out
02.5B5B19 Sept: 546M tokens, 150K requests20 Sept: 401M tokens, 97.4K requests21 Sept: 640M tokens, 123K requests22 Sept: 223M tokens, 90.5K requests23 Sept: 519M tokens, 270K requests24 Sept: 634M tokens, 257K requests25 Sept: 1B tokens, 324K requests26 Sept: 496M tokens, 315K requests27 Sept: 463M tokens, 201K requests28 Sept: 419M tokens, 253K requests29 Sept: 1.7B tokens, 530K requests30 Sept: 2.2B tokens, 701K requests1 Oct: 3.5B tokens, 942K requests2 Oct: 2.7B tokens, 786K requests3 Oct: 2.3B tokens, 638K requests4 Oct: 2B tokens, 567K requests5 Oct: 1.7B tokens, 515K requests6 Oct: 2B tokens, 515K requests7 Oct: 4.7B tokens, 1.2M requests8 Oct: 2.6B tokens, 571K requests9 Oct: 1.6B tokens, 268K requests10 Oct: 325M tokens, 62K requests11 Oct: 919M tokens, 188K requests12 Oct: 893M tokens, 189K requests13 Oct: 2.9B tokens, 678K requests14 Oct: 373M tokens, 96.5K requests15 Oct: 426M tokens, 233K requests16 Oct: 367M tokens, 99.5K requests17 Oct: 722M tokens, 185K requests18 Oct: 1.1B tokens, 223K requests19 Oct: 690M tokens, 113K requests20 Oct: 1.2B tokens, 183K requests21 Oct: 1.6B tokens, 186K requests19 Sept3 Oct17 Oct21 OctSee where it ranks on the leaderboard →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Check the source

Price date: 2026-10-18. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 11.1 (2026-10-18) ↗Coding Index: 22.4 (2026-10-18) ↗Agentic Index: 1.3 (2026-10-18) ↗
Compare this model with alternatives →