IBM: Granite 4.1 8Bibm-granite
Bottom Line
IBM: Granite 4.1 8B: $0.05/1M input, $0.10/1M output, 131K context. Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...
API Pricing (per 1M tokens)
| Input | $0.05 |
| Output | $0.10 |
| Cache Read | — |
| Cache Write | — |
| Blended (3:1) | $0.06 |
Specs & Performance
| Context Length | 131K |
| Max Output | 118K |
| Intelligence | — |
| Coding | — |
| Math | — |
| Speed | — |
| TTFT | — |
| CPS Grade | — |
| Input / Output Modalities | text → text |
More from ibm-granite
Looking for cheaper alternatives?
Find the cheapest model by task, or compare two models head-to-head.
FAQ
How much does the IBM: Granite 4.1 8B API cost?
IBM: Granite 4.1 8B costs $0.05/1M input tokens and $0.10/1M output tokens. Blended cost at a 3:1 ratio is about $0.06/1M tokens.
What is the context window of IBM: Granite 4.1 8B?
IBM: Granite 4.1 8B supports a 131K token context window with up to 118K output tokens.
Is IBM: Granite 4.1 8B worth it?
IBM: Granite 4.1 8B has a CPS grade of — (score —), intelligence index —, coding index —. Use the compare page to benchmark against rivals.