Skip to main content
IBM

Granite 4.2 8B

Granite 4.2 8B by IBM — compare inference API pricing across providers.

Input from
$0.060 / 1M tokens
across 1 provider

API Pricing

ProviderInput / 1MOutput / 1MCached / 1M
$0.060$0.250$0.015

Prices updated daily. Last check: Aug 29, 2026

Granite 4.2 8B pricing by provider

Input, output, and batch rates, plus alternatives, for one provider at a time.

Performance & Benchmarks

Source: Artificial Analysis →
Intelligence
19.6 / 100
Coding
22.4 / 100
Output Speed
148 t/s
Latency (TTFT)
247ms

Reasoning & Knowledge

  • GPQA Diamond63.1%
  • Humanity's Last Exam9.7%

Coding

  • SciCode30.4%

Agentic & Tool Use

  • Terminal-Bench v2.118.4%
  • τ-bench Banking7.6%

Instruction & Long Context

  • Long-Context Reasoning43.3%

Benchmarks measured Aug 2026. Scores are independent evaluations, not vendor-reported.

Model Details

General

Creator
IBM
Modalities
Text

Capabilities

Tool Calling
No
Open Source
No