ERNIE 4.5 21B A3B vs mistralai/Mistral-Small-3.2-24B-Instruct-2506
They cost about the same for input tokens: ERNIE 4.5 21B A3B $0.07 per M, mistralai/Mistral-Small-3.2-24B-Instruct-2506 $0.075 per M. mistralai/Mistral-Small-3.2-24B-Instruct-2506 is 1.4× cheaper for output tokens: ERNIE 4.5 21B A3B costs $0.28 per M and mistralai/Mistral-Small-3.2-24B-Instruct-2506 costs $0.20 per M. About the same: ERNIE 4.5 21B A3B takes up to 120,000 tokens of context and mistralai/Mistral-Small-3.2-24B-Instruct-2506 up to 128,000. ERNIE 4.5 21B A3B accepts text; mistralai/Mistral-Small-3.2-24B-Instruct-2506 accepts image, text.
| ERNIE 4.5 21B A3B | mistralai/Mistral-Small-3.2-24B-Instruct-2506 | |
|---|---|---|
| Model id | baidu/ernie-4.5-21B-a3b | mistralai/Mistral-Small-3.2-24B-Instruct-2506 |
| Input | $0.07 per M | $0.075 per M |
| Output | $0.28 per M | $0.20 per M |
| Context length | 120,000 tokens | 128,000 tokens |
| Accepts | text | image, 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.