IBMrouted

Granite 4.2 8B

Granite 4.2 8B is IBM's enterprise-oriented dense 8B model (Apache 2.0, August 2026) with built-in reasoning that can run in full, low-effort or non-thinking mode. IBM lists reasoning, code generation, tool calling, agentic workflows and multilingual dialogue as its strengths and names twelve tested languages, among them English, German, Spanish, French, Czech, Italian and Dutch. Small enough to be cheap, documented enough for a risk review. It is fulfilled through global providers under our European contract, and requests go only to backends that do not retain prompts or completions.

Get access API reference

model id: granite-4.2-8b

from openai import OpenAI client = OpenAI(    api_key="hb-...",    base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create(    model="granite-4.2-8b",    messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)

curl https://api.heabsy.com/v1/chat/completions \  -H "Authorization: Bearer $HEABSY_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "granite-4.2-8b",    "messages": [{"role": "user", "content": "Hello"}]  }'

import OpenAI from "openai"; const client = new OpenAI({  apiKey: process.env.HEABSY_API_KEY,  baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({  model: "granite-4.2-8b",  messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);

Context

128K tokens

Serving

Global providers · EU contract

Tool calling

Reasoning

Structured output

Vision

Input

$0.09/ 1M

Cached input

$0.06/ 1M

Output

$0.39/ 1M

Price list, updated 12 September 2026. No minimum spend, no subscription.

About the model

Developer: IBM
Released: August 2026
Licence: Apache-2.0
Architecture: dense · 8B parameters
Input: text
Reasoning: switchable per request
Languages named by the developer: English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese

Source: the developer's model card, as of 17 September 2026.

Licence: what it means for your company

Apache-2.0. A permissive open-source licence: you may use, modify and sell products built on the model, including commercially; when you redistribute the weights, the licence and copyright notices go with them.

A summary of the licence, not legal advice.

Technical details

Context window: 128K tokens
Max output: 65,536 tokens
Throughput limit: 200K tok/min
Tokenizer: Other
Streaming: yes
Open weights: ibm-granite/granite-4.2-8b

Supported parameters

max_tokens: 1 … 65536
temperature: 0 … 2
top_p: 0 … 1
frequency_penalty: -2 … 2
presence_penalty: -2 … 2
stop: array
seed: integer

Bought for you, billed by us

This model is fulfilled through global providers under our European contract: one DPA with an EU company, one invoice for every model in the catalog, no US counterparty on your paperwork. Compute may run outside the EEA — if you need strict EEA-only processing, use our own-hardware model.

Questions about this model

›Where is Granite 4.2 8B computed?

Outside the EEA, through a global provider under our European contract. You get one DPA with an EU company and one invoice, but the compute itself does not run in the EEA — we state that instead of hiding it.

›Does Granite 4.2 8B store prompts and completions?

No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.

›How large is the Granite 4.2 8B context window?

128K tokens, with up to 65,536 tokens of output.

›What does Granite 4.2 8B cost?

$0.09 per million input tokens and $0.39 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.

›Is there a throughput limit on Granite 4.2 8B?

Yes, 200K tokens per minute. Higher limits are a question of volume, not of principle.

›Which languages does Granite 4.2 8B support?

The developer names English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, Chinese. Languages not on that list may still work, but they are not claimed — test on your own material first.

›Under which licence is Granite 4.2 8B released?

›Can reasoning be switched off in Granite 4.2 8B?

Yes. Per the developer, thinking can be switched on or off for each request.

Compare with similar models

Model	Developer	Parameters	Context	Licence	Input / 1M
Granite 4.2 8B	IBM	8B	128K	Apache-2.0	$0.09
Llama 3.1 8B Instruct	Meta	8B	128K	Llama 3.1 Community License	$0.08
Qwen3.5 9B	Qwen (Alibaba)	9B	256K	Apache-2.0	$0.15
gpt-oss-20b	OpenAI	21B / 3.6B	128K	Apache-2.0	$0.05