IBM models
llm11 can call 2 IBM models through one API, with Jev, TypeSafe AI's System One model, deciding which one answers each request. Blended prices run from $0.041 to $0.107 per million tokens. The newest is Granite 4.2 8B, released 2026-08-31.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Granite 4.2 8B | $0.060 | $0.250 | 131K | |
| Granite 4.0 Micro | $0.017 | $0.112 | 131K |
Read from the live catalogue and refreshed daily. Prices are per million tokens.
Questions
- Which IBM models can I call through llm11?
- 2 today, listed with live prices on this page. The list follows the upstream catalogue, so a new IBM model appears here without anyone editing the page.
- What is the cheapest and the most expensive IBM model?
- By blended price, weighting three parts input to one part output: Granite 4.0 Micro is cheapest at $0.041 per million tokens, and Granite 4.2 8B is the most expensive at $0.107.
- What is the newest IBM model?
- Granite 4.2 8B, released 2026-08-31. Call it with model set to ibm-granite/granite-4.2-8b.