Which has the larger context window, Granite-4.0-H-Small or Llama 4 Maverick 17B 128E Instruct FP8?

Both models offer a similar context window.

Granite-4.0-H-Small vs Llama 4 Maverick 17B 128E Instruct FP8

Q: Is Granite-4.0-H-Small or Llama 4 Maverick 17B 128E Instruct FP8 cheaper?

Granite-4.0-H-Small is cheaper on output tokens ($0.27 vs $1.48 per 1M).

Granite-4.0-H-Small is cheaper on output tokens. Choose Granite-4.0-H-Small or Llama 4 Maverick 17B 128E Instruct FP8 based on the trade-off between cost, context, and the benchmarks that matter for your use case.

Spec	Granite-4.0-H-Small	Llama 4 Maverick 17B 128E Instruct FP8
Provider	watsonx.ai	watsonx.ai
Input / 1M tokens	$0.06	$0.37
Output / 1M tokens	$0.27	$1.48
Context window	131K	131K
Parameters	—	—
Open weights	Yes	Yes
Released	Oct 2025	Apr 2025

Granite-4.0-H-Small details →Llama 4 Maverick 17B 128E Instruct FP8 details →

FAQ

Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.