ibm-granite/granite-4.2-30b vs openai/gpt-oss-120b-Ultra
ibm-granite/granite-4.2-30b is 1.3× cheaper for input tokens: ibm-granite/granite-4.2-30b costs $0.16 per M and openai/gpt-oss-120b-Ultra costs $0.20 per M. ibm-granite/granite-4.2-30b is 1.5× cheaper for output tokens: ibm-granite/granite-4.2-30b costs $0.65 per M and openai/gpt-oss-120b-Ultra costs $0.95 per M. Both read up to 131,072 tokens of context.
| ibm-granite/granite-4.2-30b | openai/gpt-oss-120b-Ultra | |
|---|---|---|
| Model id | ibm-granite/granite-4.2-30b | openai/gpt-oss-120b-Ultra |
| Input | $0.16 per M | $0.20 per M |
| Output | $0.65 per M | $0.95 per M |
| Context length | 131,072 tokens | 131,072 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | deepinfra | deepinfra |
Prices are the providers' list prices per million tokens, as of . Both run on your own provider key through one OpenAI-compatible endpoint, with no fee on the tokens.