API pricing
IBM API pricing
IBM API prices run from $0.017 per million input tokens (Granite 4.0 Micro) to $0.06 (Granite 4.2 8B). Its highest-ranked model, Granite 4.2 8B, costs $0.06 input and $0.25 output per million tokens.
Last verified
| Cached input | ||||||
|---|---|---|---|---|---|---|
| Granite 4.0 Micro (open weights) | $0.017 | $0.11 | — | $0.0408 | 131K | 29.0 |
| Granite 4.2 8B (open weights) | $0.06 | $0.25 | $0.015 | $0.11 | 131K | 40.5 |
Prices on other platforms
The same models are often sold through clouds and resellers at different rates.
| Model | Route | Input | Output | Checked |
|---|---|---|---|---|
| Granite 4.2 8B | openrouter | $0.06 | $0.25 | 2026-10-10 |
| Granite 4.0 Micro | openrouter | $0.017 | $0.11 | 2026-10-10 |
Frequently asked questions
How much does the IBM API cost?
IBM API prices run from $0.017 per million input tokens (Granite 4.0 Micro) to $0.06 (Granite 4.2 8B). Its highest-ranked model, Granite 4.2 8B, costs $0.06 input and $0.25 output per million tokens.
Does IBM discount cached input?
Yes. Cached input is billed at a lower rate on 1 of the 2 priced models; the cached rate is listed next to each model.