When was Granite 4.2 8B released?

IBM released Granite 4.2 8B on 25 Aug 2026. It is available through the Opper gateway.

Does Granite 4.2 8B support zero data retention?

Yes. Granite 4.2 8B is available with zero data retention on DeepInfra through the Opper gateway.

Where is Granite 4.2 8B hosted?

Granite 4.2 8B runs on US hosting routes through the Opper gateway.

Is Granite 4.2 8B trained on prompts and outputs?

No. Every hosting route for Granite 4.2 8B is configured so customer prompts and outputs are not used to train models by default.

Is a GDPR DPA available for Granite 4.2 8B?

Yes. A GDPR Data Processing Agreement is available on at least one route serving Granite 4.2 8B. Contact hello@opper.ai to receive it.

Granite 4.2 8B

by IBM

Announcement · All IBM releases

Granite 4.2 8B is the mid-size reasoning model of IBM's Granite 4.2 family, released on August 25, 2026 and post-trained from Granite 4.1 8B Base. It is a dense decoder-only transformer that reasons step by step inside think tags before it answers; thinking is on by default and can be switched off per request or reduced to a low-effort mode when latency matters more than depth. IBM trained it with supervised fine-tuning and several rounds of reinforcement learning, including agentic phases on software engineering, terminal use and web search with trajectories of up to 200 tool-calling turns, so it plans which tools to call and why. It natively supports a 128K-token context, with a long-context extension to 512K, and is tested in English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch and Chinese. The weights are released under Apache 2.0, alongside 3B and 30B siblings in the same family.

Call Granite 4.2 8B on Opper with the OpenAI SDK. Sign up without a credit card. Get started

Get your API key Try in chat Compare

Key info

Input

Output

Features

Context window

131K

Max output

—

Input price

$0.06 /1M$0.01 cache read

Output price

$0.25 /1M

Released

25 Aug 2026

Web search

Via Opper

US residency available
Zero data retention on pay-as-you-go
No training by default
GDPR DPA available

Available routes

Granite 4.2 8B runs on 1 route through the Opper gateway. Compare residency, zero data retention and training posture at a glance, with full data-handling detail per route below.

Provider	Region	Zero data retention	Training	Input	Output	Cache read
DeepInfra	US		No	$0.06	$0.25	$0.01

Live routes and prices as JSON: api.opper.ai/v3/models?q=deepinfra%2Fibm-granite%2Fgranite-4.2-8b

Uptime and availability

Granite 4.2 8B runs on a single route through the Opper gateway today, so its availability is that provider's availability.

99.86%route uptime, last 30 days

Single route, no failover target within this model.

Name a second model in the same request and the gateway tries it on retriable errors, so a busy hour never has to reach your users. Set up a fallback chain.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. See uptime for every provider Opper monitors.

Data handling per route

Each route hosting Granite 4.2 8B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

DeepInfra — United States🇺🇸

Zero data retention: nothing is logged, held for abuse monitoring or used for training. No training on customer data. US; SCCs; DPA available.

Zero data retention: Yes. Nothing is logged, held for abuse monitoring or used for training.
Training: No training on customer data.
Logging: None
Abuse monitoring: No classifier
GDPR DPA: DPA available
Transfer mechanism: SCCs

Best for

Where Granite 4.2 8B ranks among the models on Opper with a score for each use case.

Legal14.6

Legal tasks and reasoningSee the Legal ranking →Finance14.8

Finance and accountingSee the Finance ranking →Agents1.1

Terminal-Bench 4.0 and AutomationBenchSee the Agents ranking →

Benchmarks

Independent benchmark scores: the Intelligence Index and the individual evaluations behind it, grouped by skill.

Global rank#246 of 506 LLMs

TierEfficient

Output speed61 tok/s

Intelligence Index (previous version)11.1

Coding

Terminal-Bench 4.0

SciCode

32%

Agentic & knowledge work

AutomationBench

GDPval

GDP.pdf

Briefcase (Elo)310

Science & reasoning

Terminal-Bench Science

CritPt (hard)

HLE Diamond

Humanity's Last Exam

10%

GPQA Diamond

63%

Long-context reasoning

45%

Knowledge

Omniscience-16.7

By domain

Finance & accounting

14.8

Legal

14.6

Economics

14.6

Strategy & operations

6.9

See full leaderboard →Benchmarks via Artificial Analysis · View on AA

Get started

Call Granite 4.2 8B through the Opper gateway with one API key. Opper is drop-in compatible with the OpenAI, Anthropic and Google AI SDKs.

Granite 4.2 8B is a premium model on Opper. Sign up needs no credit card: you get an API key straight away and the free models work in the playground and the API. Add a card to use premium models, pay-as-you-go with no minimum.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up Opper for you.

Or call it directly

1import OpenAI from "openai";
2
3const client = new OpenAI({
4  apiKey: process.env.OPPER_API_KEY,
5  baseURL: "https://api.opper.ai/v3/compat",
6});
7
8const completion = await client.chat.completions.create({
9  model: "deepinfra/ibm-granite/granite-4.2-8b",
10  messages: [{ role: "user", content: "Hello" }],
11});
12console.log(completion.choices[0].message.content);