MiniMaxAI/MiniMax-M2.7-Turbo vs ERNIE-4.5-VL-28B-A3B-Thinking
They cost about the same for input tokens: MiniMaxAI/MiniMax-M2.7-Turbo $0.38 per M, ERNIE-4.5-VL-28B-A3B-Thinking $0.39 per M. ERNIE-4.5-VL-28B-A3B-Thinking is 4.4× cheaper for output tokens: MiniMaxAI/MiniMax-M2.7-Turbo costs $1.70 per M and ERNIE-4.5-VL-28B-A3B-Thinking costs $0.39 per M. MiniMaxAI/MiniMax-M2.7-Turbo reads more: MiniMaxAI/MiniMax-M2.7-Turbo takes up to 196,608 tokens of context and ERNIE-4.5-VL-28B-A3B-Thinking up to 131,072. MiniMaxAI/MiniMax-M2.7-Turbo accepts text; ERNIE-4.5-VL-28B-A3B-Thinking accepts image, text.
| MiniMaxAI/MiniMax-M2.7-Turbo | ERNIE-4.5-VL-28B-A3B-Thinking | |
|---|---|---|
| Model id | MiniMaxAI/MiniMax-M2.7-Turbo | baidu/ernie-4.5-vl-28b-a3b-thinking |
| Input | $0.38 per M | $0.39 per M |
| Output | $1.70 per M | $0.39 per M |
| Context length | 196,608 tokens | 131,072 tokens |
| Accepts | text | image, text |
| Produces | text | text |
| Served by | deepinfra | 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.