CtrlAltDebrief

Granite 4.2 8B

IBMFirst listed Sep 2026
ReasoningPrompt caching
Compare Granite 4.2 8BCount tokens for Granite 4.2 8B
Context
131K
Max output
118K
Serving providers
2
Cheapest input
$0.06 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
61 t/s
tokens / second
Time to first token
0.75s
latency
Headline indices
Intelligence Index
11.1
of 100
Coding Index
22.4
of 100
Frozen Sep 9, 2026
Agentic Index
3.7
of 100
Frozen Sep 9, 2026
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
Automation Bench0.0default—
CritPt0%default—
GDPval (normalized)Frozen Aug 18, 20260%default—
GPQA Diamond63%default—
Humanity's Last Exam10%default—
Long-Context Reasoning45%default—
Omniscience-17.2default—
Omniscience Accuracy0.1default—
Omniscience Non Hallucination0.7default—
SciCode31%default—
Terminal Bench400default—
TerminalBench v2.118%default—
τ-bench Banking8%default—
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.06 to $0.10 per 1M tokens across 2 providers, so the dearest route costs 67% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
OpenRouterRouted quote$0.06$0.251
Standardibm-granite/granite-4.2-8b
ComponentUnitStandard
Text cached in/1M tok$0.015
Text input/1M tok$0.06
Text output/1M tok$0.25
Wandb$0.10$0.151

Price history

OpenRouter routed quote

OpenRouter's price is a routed quote. It moves with whichever upstream route OpenRouter prefers that day, so we do not track it as a price history.

Cost calculator

estimate your monthly spend on this model
$32
estimated / month

Model IDs

copy the exact identifier for your platform
ibm-granite/granite-4.2-8bwandb/ibm-granite/granite-4.2-8b

Frequently asked questions

Granite 4.2 8B pricing, context and availability

How much does Granite 4.2 8B cost?

Granite 4.2 8B costs $0.06 per 1M input tokens as an OpenRouter routed quote, and $0.15 per 1M output tokens from Wandb. An OpenRouter routed quote is the price of whichever upstream provider OpenRouter prefers today, so it moves day to day. Across 2 serving providers, input prices range from $0.06 to $0.10 per 1M tokens.

What is the context window of Granite 4.2 8B?

Granite 4.2 8B accepts up to 131K tokens of context and can return up to 118K output tokens.

Which providers serve Granite 4.2 8B?

Granite 4.2 8B is available from 2 serving providers, each with its own pricing and model ID. OpenRouter is currently the cheapest, as a routed quote.

What can Granite 4.2 8B do?

Granite 4.2 8B supports reasoning and prompt caching.

Other IBM models

compare pricing across the IBM lineup
Granite 4.0 Micro$0.017/1M · 2 providersGranite 3.3 8B Instruct$0.03/1M · 2 providersGranite 4.1 8B$0.05/1M · 2 providersGranite 4 H Small$0.0636/1M · 1 providerGranite Guardian 3.2 2B$0.10/1M · 1 providerGranite Vision 3.2 2B$0.10/1M · 1 providerGranite 3 8B Instruct$0.20/1M · 1 providerGranite Guardian 3.3 8B$0.20/1M · 1 provider
Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI