Last refreshed 2026-05-19. Next refresh: weekly.
Why use Granite 8B Code on RHEL AI?
RHEL AI offers Granite 8B Code with competitive pricing. Red Hat, a subsidiary of IBM since 2019, is a pioneering technology company that has been at the forefront of open-source software development since its founding in 1993.
Compare Granite 8B Code across 3 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: granite-8b-codegranite-8b-codeRequest example
granite-8b-code.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare Granite 8B Code Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| RHEL AI | — | — |
| IBM watsonx | $0.60 | $0.60 |
Capabilities
No model capability flags are currently sourced.
About Granite 8B Code
Granite 8B Code is IBM Research's Granite Code model. It is deprecated (originally released 2024-05-06); use it only for reproducing earlier results or evaluating drift over time.
FAQ
What is the context window for Granite 8B Code on RHEL AI?
Granite 8B Code supports a 8k token context window on RHEL AI.
How does RHEL AI compare to other Granite 8B Code providers?
Granite 8B Code is available from 3 providers. The cheapest input pricing is $0.6/1M tokens from IBM watsonx.
Who created Granite 8B Code?
Granite 8B Code was created by IBM Research as part of the Granite Code model family.
Is Granite 8B Code open source?
Granite 8B Code is open source under Apache 2.0 according to the seed data.