All AI models · LLM benchmarks · Methodology

IBM

Granite-4.0-H-Small

Open-weight hybrid model for enterprise chat, coding, retrieval-augmented generation, and tool-calling workloads

Model facts

Context window
131K tokens
Maximum output
131K tokens
Cheapest paid input
$0.064 per 1M tokens
Cheapest paid output
$0.265 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

tool calling, structured output, temperature control, open weights, text.

Artificial Analysis benchmarks

Compare this model on the full LLM benchmark leaderboard.

ConfigurationAAICodingMathOutput tokens/s
default4.9not measured13.741.6

Observed price history

  • 2026-08-24: $0.064 input / $0.265 output per 1M tokens

API providers

  • watsonx.ai — model id ibm/granite-4-h-small; $0.064 input / $0.265 output per 1M tokens; provider documentation