ERNIE 4.5 300B A47B vs google/gemma-4-31B-it-Ultra
They cost about the same for input tokens: ERNIE 4.5 300B A47B $0.28 per M, google/gemma-4-31B-it-Ultra $0.27 per M. google/gemma-4-31B-it-Ultra is 1.4× cheaper for output tokens: ERNIE 4.5 300B A47B costs $1.10 per M and google/gemma-4-31B-it-Ultra costs $0.76 per M. About the same: ERNIE 4.5 300B A47B takes up to 123,000 tokens of context and google/gemma-4-31B-it-Ultra up to 131,072. ERNIE 4.5 300B A47B accepts text; google/gemma-4-31B-it-Ultra accepts image, text.
| ERNIE 4.5 300B A47B | google/gemma-4-31B-it-Ultra | |
|---|---|---|
| Model id | baidu/ernie-4.5-300b-a47b-paddle | google/gemma-4-31B-it-Ultra |
| Input | $0.28 per M | $0.27 per M |
| Output | $1.10 per M | $0.76 per M |
| Context length | 123,000 tokens | 131,072 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.