Granite 4.0 H Small
Developed by IBM
API Pricing (per 1M tokens)
Input$0.06
Output$0.25
Intelligence Benchmarks
MMLU Pro62.4%
GPQA41.6%
Intelligence Index10.8
LivebenchN/A
Technical Specifications
| Context Window | 128K Tokens |
|---|
| Vision Support | No |
|---|
| Tokens per Second | 436 |
|---|
| Time to First Token (s) | 8.85 |
|---|
| Modalities | text->text |
|---|