Granite 4.1 8B

IBM Granite chattool_use

API ID: ibm-granite/granite-4.1-8b-20260429

Compare Calculate
Input Price
$0.05
/1M tokens
Output Price
$0.10
/1M tokens
Cached Input
$0.05
Save 0%

About Granite 4.1 8B

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

📊
Price Ranking
#624 lowest price among 1240 Chat models

Model Specifications

Context Length
131k
Max Output
131k
Release Date
2026-04-30
Capabilities
chat tool_use
Input Modalities
text
Output Modalities
text

Best For

  • Conversations, content writing, general assistance

Consider Alternatives For

  • Image understanding (needs vision capability)

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Personal AI Assistant
$0.05
/month
50 conversations/day, ~500 tokens each
Customer Service Bot
$1.65
/month
1000 tickets/day, ~800 tokens each
Calculate Your Custom Usage

IBM Granite Model Lineup

Compare all models from IBM Granite to find the best fit

Model Input Output Context Capabilities
Granite 4.1 8B Current $0.05 $0.10 131k chat tool_use
Granite 4.0 Micro $0.02 $0.11 131k chat
View All IBM Granite Models →

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Google Gemma 3 4B
Google
Input: $0.05
Output: $0.10
Context: 131k
Google Gemini Embedding 001
Google
Input: $0.15
Output: Free
Context: 20k
Mistral Codestral Embed 2505
Mistral
Input: $0.15
Output: Free
Context: 8k
Microsoft Phi 4 Multimodal Instruct
Microsoft
Input: $0.05
Output: $0.10
Context: 131k
Compare These Models

💡 Cheaper Alternatives

Same Brand (IBM Granite)

Granite 4.0 Micro
$0.02 $0.11 131k

Cross Brand

GTE-Base Other
$0.0050 Free 512
E5-Base-v2 Other
$0.0050 Free 512
paraphrase-MiniLM-L6-v2 Other
$0.0050 Free 512

🚀 Quick Start

Get started with Granite 4.1 8B API

OpenAI-compatible SDK 
from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="ibm-granite/granite-4.1-8b-20260429",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Resources

Continue Your Decision

Back to IBM Granite Add to Compare Calculate Cost