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.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 4.9 | not measured | 13.7 | 41.6 |
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