Baichuan M2 32B vs ERNIE-4.5-21B-A3B-Thinking
They cost about the same for input tokens: Baichuan M2 32B $0.07 per M, ERNIE-4.5-21B-A3B-Thinking $0.07 per M. Baichuan M2 32B is 4× cheaper for output tokens: Baichuan M2 32B costs $0.07 per M and ERNIE-4.5-21B-A3B-Thinking costs $0.28 per M. Both read up to 131,072 tokens of context.
| Baichuan M2 32B | ERNIE-4.5-21B-A3B-Thinking | |
|---|---|---|
| Model id | baichuan/baichuan-m2-32b | baidu/ernie-4.5-21B-a3b-thinking |
| Input | $0.07 per M | $0.07 per M |
| Output | $0.07 per M | $0.28 per M |
| Context length | 131,072 tokens | 131,072 tokens |
| Accepts | text | text |
| Produces | text | text |
| Served by | novita | novita |
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.