IBM · Updated 4 November 2026

Granite 4.2 8B

Intelligence
5 · 50th of 54
Coding
Not scored yet
Price per 1M tokens
$0.11 blended · $0.06 input · $0.25 output
Output speed
75 tok/s
Time to first token
0.4 s
Context window
131K tokens
Open weights
Yes
Released
25 August 2026

How it compares

#ModelIntelligenceCodingPrice / 1M tokensSpeedContext
1Granite 4.2 8B IBM · open weights5—$0.1175 tok/s131K
2Gemini 4 Carbon Google60—$8.0092 tok/s—
3Gemini 3.1 Flash-Lite Google6—$0.56—1M
4Nemotron 3.5 Lightning NVIDIA · open weights6—$0.10271 tok/s262K
5Granite 4.2 3B IBM5————

Cheaper alternative within 3 points: Nemotron 3.5 Lightning at $0.10 per million tokens.

Data: Artificial Analysis (intelligence and coding indexes, prices, speed) and OpenRouter (open weights, context windows). Updated 4 November 2026; refreshed every 6 hours.

More rankings