Granite 4 H Small
Provider: watsonx ·
watsonx/ibm/granite-4-h-small Pricing per million tokens
| Component | USD per 1M tokens |
|---|---|
| Input | $0.06 |
| Output | $0.25 |
Monthly cost estimates
Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.
Small
1M in / 200k out
$0.11
per month
Medium
10M in / 2000k out
$1.10
per month
Large
100M in / 20000k out
$11.00
per month
Context
- Input window
- 20,480 tokens
- Max output
- 20,480 tokens
Capabilities
- ⬜ Vision (image input)
- ✅ Function / tool calling
- ⬜ Prompt caching
- ⬜ Web search
- ⬜ JSON / response schema
Compare Granite 4 H Small with similar models
Mistral Small 2503
watsonx
$0.10 in
/ $0.30 out
Mistral Small 3 1 24b Instruct 2503
watsonx
$0.10 in
/ $0.30 out
Granite Guardian 3 2 2b
watsonx
$0.10 in
/ $0.10 out
Granite Vision 3 2 2b
watsonx
$0.10 in
/ $0.10 out
Llama 3 2 1b Instruct
watsonx
$0.10 in
/ $0.10 out
Granite 3 8b Instruct
watsonx
$0.20 in
/ $0.20 out
Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.