IBM Granite: Granite 4.2 8B
ibm-granite/granite-4.2-8b
Access Granite 4.2 8B from IBM Granite using Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "ibm-granite/granite-4.2-8b"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "ibm-granite/granite-4.2-8b"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="ibm-granite/granite-4.2-8b",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "ibm-granite/granite-4.2-8b",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Granite 4.2 8B is a dense, decoder-only language model from IBM, post-trained from Granite 4.1 8B Base with native reasoning added on top. It switches between three modes: full chain-of-thought thinking, a low-effort abbreviated reasoning mode for easy questions, and non-thinking for direct answers, so the reasoning budget can be tuned per request.
It was trained with agentic reinforcement learning to call tools, edit and run code, drive a terminal, and search the web inside real environments, and it emits tool calls in the OpenAI function-calling format for direct use with existing agent frameworks. It supports a 128K-token context window and 12 languages including English, German, Spanish, French, Japanese, and Chinese.
On benchmarks, it scores 47.67 on SWE-Bench Verified, 86.67 on AIME25, 74.04 on MMLU-Pro, and 65.19 on Arena-Hard-v2, and it posts an Artificial Analysis Intelligence Index score of 20, well above the median of 9 for open-weight models of similar size. Released under Apache 2.0, it's a solid pick for agentic coding, tool-calling workflows, and multilingual tasks at a dense 8B parameter count.
Context Window 131K
tokens
Max Output 118K
tokens
Input Cost $0.1
per million tokens
Output Cost $0.15
per million tokens
Release Date Aug 31, 2026
Model Playground
Try Granite 4.2 8B instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
More AI Models From IBM Granite
Find other IBM Granite models →
Granite 4.1 8B
IBM Granite 4.1 8B is a dense, decoder-only language model from IBM, built for enterprise workloads like tool calling, RAG, code generation, summarization, and classification. It supports a 131K-token context window and 12 languages including English, German, Spanish, French, Japanese, and Chinese. Despite its compact size, the 8B model matches or outperforms IBM's previous-generation 32B Mixture-of-Experts model across benchmarks — scoring 69.0 on ArenaHard, 68.3 on BFCL V3 (tool calling), and 92.5 on GSM8K. It implements OpenAI-compatible tool calling and supports fill-in-the-middle for code completion. Its dense architecture makes it straightforward to fine-tune for downstream tasks. Released under the Apache 2.0 license, it's a strong pick for developers who need reliable enterprise capabilities at an efficient parameter count.
ChatGranite 4.0 Micro
Granite 4.0 Micro is a 3B-parameter dense language model from IBM, built on a conventional transformer architecture and optimized for low-latency, cost-efficient workloads. Despite its compact size, it significantly outperforms its predecessor Granite 3.3 8B across the board — a model more than twice its size. It scores 16 on the Artificial Analysis Intelligence Index, placing ahead of Gemma 3 4B (15). In RAG benchmarks, it outperforms much larger models including Llama 3.3 70B and Qwen3 8B. The model natively supports tool calling, function calling, multilingual generation, fill-in-the-middle code completion, RAG, and structured JSON output, with a 128K token context window. It's a strong fit for agentic sub-tasks, API orchestration, and scenarios where speed and cost matter more than peak reasoning power.
Frequently Asked Questions
You can access Granite 4.2 8B by IBM Granite through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Granite 4.2 8B to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.1 |
| Output | $0.15 |
Granite 4.2 8B was created by IBM Granite and released on Aug 31, 2026.
Granite 4.2 8B supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
Granite 4.2 8B can generate up to 118K tokens in a single response.
Yes — the Granite 4.2 8B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add Granite 4.2 8B to your app without worrying about API keys or setup.
Read the Docs View Tutorials