DeepSeek R1 Distill Qwen 14B vs ibm-granite/granite-4.2-30b
They cost about the same for input tokens: DeepSeek R1 Distill Qwen 14B $0.15 per M, ibm-granite/granite-4.2-30b $0.16 per M. DeepSeek R1 Distill Qwen 14B is 4.3× cheaper for output tokens: DeepSeek R1 Distill Qwen 14B costs $0.15 per M and ibm-granite/granite-4.2-30b costs $0.65 per M. ibm-granite/granite-4.2-30b reads more: DeepSeek R1 Distill Qwen 14B takes up to 32,768 tokens of context and ibm-granite/granite-4.2-30b up to 131,072.
| DeepSeek R1 Distill Qwen 14B | ibm-granite/granite-4.2-30b | |
|---|---|---|
| Model id | deepseek/deepseek-r1-distill-qwen-14b | ibm-granite/granite-4.2-30b |
| Input | $0.15 per M | $0.16 per M |
| Output | $0.15 per M | $0.65 per M |
| Context length | 32,768 tokens | 131,072 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | novita | 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.