LLM Pricing

← All Models

IBM: Granite 4.1 8B

🇺🇸 IBM Granite · Granite 4.1

Input Price $0.050 per million tokens NT$1.6
Output Price $0.100 per million tokens NT$3.2
Context Window 131K tokens Output limit: 131K
OpenRouter Route Price Please verify with official pricing pages
Use this model via OpenRouter →

Overview

IBM: Granite 4.1 8B is a large language model API from IBM Granite, part of its Granite 4.1 model family. At $0.050 per million input tokens and $0.100 per million output tokens, it sits in the budget tier — among the cheaper options for high-throughput or cost-sensitive workloads. Output tokens cost about 2× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. The 131K-token context window — around 197 pages of text — comfortably handles long documents, multi-file code, or extended conversations. On Artificial Analysis's Intelligence Index it scores 7 (F grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.

Dimension Unit Price (USD) Price (TWD) Effective From
Input per 1M tokens $0.050 NT$1.6
Output per 1M tokens $0.100 NT$3.2
Cached Input per 1M tokens $0.050 NT$1.6

Provider
IBM Granite
Model Family
Granite 4.1
Version String
ibm-granite/granite-4.1-8b
Status
Active
Modality
Text
Context Window
131,072 tokens
Output Limit
131,072 tokens

Index Metrics

Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis

Coding Index 10 F Measured: 2026-07-01
Intelligence Index 7 F Measured: 2026-07-01

Benchmark Scores

Data source: Artificial Analysis

AA-LCR 12.0% F Measured: 2026-07-01
GPQA Diamond 43.3% D Measured: 2026-07-01
HLE 3.8% D Measured: 2026-07-01
IFBench 38.6% D Measured: 2026-07-01
Non-Hallucination 12.7% Measured: 2026-07-01
Omniscience Accuracy 12.1% Measured: 2026-07-01
SciCode 21.8% C Measured: 2026-07-01
Tau2 27.8% Measured: 2026-07-01

Performance Metrics

Real-world benchmarks, updated every 72 hours by Artificial Analysis — Artificial Analysis

First Token Latency 0.8s Measured: 2026-07-01
Output Speed 120 t/s Measured: 2026-07-01
Response Time 5.0s Measured: 2026-07-01

90-Day Price Trend

Input / Output price (USD per 1M tokens)

Past 90 days of records; every price change is shown here

Date Dimension Price (USD) Source
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter
Input $0.050 OpenRouter
Cached Input $0.050 OpenRouter
Output $0.100 OpenRouter

Key Insights

Key data points from this page for quick reference and citation.

  • IBM: Granite 4.1 8B Input price: $0.05/M tokens
  • IBM: Granite 4.1 8B Output price: $0.1/M tokens
  • Context window: 131,072 tokens
  • Provider: IBM Granite
  • Model family: Granite 4.1
  • Modalities: Text
  • Data source: OpenRouter, updated daily