Granite 4.2 8B API

Q: What is the Granite 4.2 8B model ID?

Use ibm-granite/granite-4.2-8b as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Try this model

IBM's dense 8B reasoning model with configurable reasoning effort and Apache 2.0 licensing.

Modalities: TextText
In / Out price: $0.1058/$0.2645per 1M
Context window: 128K tokens
Released: Aug 31, 2026

Granite 4.2 8B overview

Granite 4.2 8B by IBM

Granite 4.2 8B is IBM's dense reasoning model, fine-tuned from Granite 4.1 8B, with configurable reasoning effort, tool calling and structured outputs over a 131K-token context.

Granite 4.2 8B specs

Model ID: ibm-granite/granite-4.2-8b
Developer: IBM
Context window: 131,072 tokens
Max output: 117,964 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What Is Granite 4.2 8B?

Granite 4.2 8B is IBM's dense reasoning model, fine-tuned from Granite 4.1 8B for mathematics, code generation, multilingual dialogue and agentic workflows that need multi-step reasoning.

Reasoning is on by default and its effort is configurable, high, low or none, so the same endpoint serves both quick lookups and deliberate multi-step work.

Technical Specifications

Context window: 131,072 tokens
Tool calling and structured outputs

Where Granite 4.2 8B Fits

Agentic workflows
Tool calling and structured outputs suit agent loops that plan, call tools and iterate.

Cost-sensitive reasoning
Turning reasoning effort down keeps routine calls cheap, while high effort stays available when the task needs it.

Available on AI/ML API since August 31, 2026.

Use cases

Granite 4.2 8B is documented as suitable for reasoning-intensive enterprise applications, with IBM describing it as a balanced reasoning model for general-purpose enterprise use. It is also suited to complex math and multi-step logic tasks.

The model is documented for coding-related work, including code generation and software engineering workflows. IBM also says Granite 4.2 can support terminal-based coding and other multi-step development tasks in agentic settings.

It is documented for tool-calling and agentic workflows, including evaluating which applications to use and in what order, and integrating with agent frameworks. The model is also described as useful for search-driven workflows and web-search-based agent behavior.

It is documented for multilingual dialogue tasks and multilingual use cases. The model is also listed as suitable for structured output or structured data extraction in provider documentation.

Capabilities

Reasoning
Streaming
Structured outputs
Function calling

Granite 4.2 8B benchmarks by Artificial Analysis

See how Granite 4.2 8B compares in intelligence, generation speed, cost per task and latency. Data retrieved Nov 3, 2026.

Intelligence#47 / 505.1Index v5.0 Speed#158 / 21961.1Output tokens / second Cost per task#3 / 44$0.0405USD / benchmark task Latency#54 / 2160.92Seconds to first token

Intelligence

Index v5.0

Speed

Output tokens / second

Cost per task

USD / benchmark task

Benchmark results

Compare 18 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Granite 4.2 8B API pricing

Granite 4.2 8B pricing in US dollars
Usage	Price	Unit
Input	$0.1058	1M tokens
Output	$0.2645	1M tokens
Cached input	$0.0529	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Granite 4.2 8B vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Granite 4.2 8B	$0.1058	$0.2645
Schematron V2 Small	$0.0529	$0.2433
Nova Lite 1.0	$0.0635	$0.2539
Llama Guard 2 (8B)	$0.26	$0.26
Mistral (7B) Instruct v0.2	$0.26	$0.26

How to use the Granite 4.2 8B API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "ibm-granite/granite-4.2-8b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "ibm-granite/granite-4.2-8b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "ibm-granite/granite-4.2-8b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Granite 4.2 8B FAQ

What is Granite 4.2 8B?

Granite 4.2 8B is an 8-billion-parameter dense reasoning model from IBM, fine-tuned from Granite 4.1 8B for mathematics, code generation, multilingual dialogue and agentic workflows.

What licence is Granite 4.2 8B released under?

Apache 2.0, which permits unrestricted commercial use. IBM also publishes cryptographic signatures for the weights and holds ISO certification for the development process.

How do you control how much Granite 4.2 8B reasons?

Reasoning is on by default and its effort is configurable: high, low or none. That lets you keep routine calls short and reserve deliberate reasoning for the requests that need it.

Does Granite 4.2 8B produce chain-of-thought reasoning?

Yes. Reasoning is emitted natively inside think tags, which IBM reports improves results on math, coding and multi-step problems.

Does Granite 4.2 8B support tool calling?

Yes, the model supports function calling.

What architecture does Granite 4.2 8B use?

A dense, decoder-only transformer built on 40 layers, using Grouped Query Attention and Rotary Position Embeddings.

Is Granite 4.2 8B multimodal?

No. Granite 4.2 8B takes text and returns text.

Can Granite 4.2 8B be self-hosted?

Yes. The Apache 2.0 licence and published weights allow local or on-premise deployment, and the 8B size keeps hardware requirements modest.

How do I call Granite 4.2 8B on AI/ML API?

Send a request to the chat completions endpoint with the model id ibm-granite/granite-4.2-8b.

What is the Granite 4.2 8B model ID?

Use ibm-granite/granite-4.2-8b as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.

Start building with Granite 4.2 8B

Get API key

Granite 4.2 8B API

ibm-granite/granite-4.2-8b

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "ibm-granite/granite-4.2-8b",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "ibm-granite/granite-4.2-8b",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "ibm-granite/granite-4.2-8b",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Granite 4.2 8B API

Granite 4.2 8B overview

Granite 4.2 8B by IBM

Granite 4.2 8B specs

What Is Granite 4.2 8B?

Technical Specifications

Where Granite 4.2 8B Fits

Use cases

Capabilities

Granite 4.2 8B benchmarks by Artificial Analysis

Intelligence

Speed

Cost per task

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Granite 4.2 8B API pricing

Granite 4.2 8B vs other models: token prices

How to use the Granite 4.2 8B API

Build with your agent

1Get your API key

2Make your first request

Related articles

Granite 4.2 8B FAQ

Start building with Granite 4.2 8B

Granite 4.2 8B API

Build with your agent

1Get your API key

2Make your first request

Granite 4.2 8B API

Granite 4.2 8B overview

Granite 4.2 8B by IBM

Granite 4.2 8B specs

What Is Granite 4.2 8B?

Technical Specifications

Where Granite 4.2 8B Fits

Use cases

Capabilities

Intelligence

Speed

Cost per task

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Granite 4.2 8B API pricing

Granite 4.2 8B vs other models: token prices

How to use the Granite 4.2 8B API

Build with your agent

1Get your API key

2Make your first request

Models similar to Granite 4.2 8B

Seed-2.0-Mini

LFM2.5-24B-A2B

Reka Edge

Solar Mini 4

Voxtral Small 24B 2507

Reka Flash 3

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Granite 4.2 8B FAQ

Start building with Granite 4.2 8B