ERNIE-4.5-VL-28B-A3B-Thinking vs DeepSeek V3 Turbo
They cost about the same for input tokens: ERNIE-4.5-VL-28B-A3B-Thinking $0.39 per M, DeepSeek V3 Turbo $0.40 per M. ERNIE-4.5-VL-28B-A3B-Thinking is 3.3× cheaper for output tokens: ERNIE-4.5-VL-28B-A3B-Thinking costs $0.39 per M and DeepSeek V3 Turbo costs $1.30 per M. ERNIE-4.5-VL-28B-A3B-Thinking reads more: ERNIE-4.5-VL-28B-A3B-Thinking takes up to 131,072 tokens of context and DeepSeek V3 Turbo up to 64,000. ERNIE-4.5-VL-28B-A3B-Thinking accepts image, text; DeepSeek V3 Turbo accepts text.
| ERNIE-4.5-VL-28B-A3B-Thinking | DeepSeek V3 Turbo | |
|---|---|---|
| Model id | baidu/ernie-4.5-vl-28b-a3b-thinking | deepseek/deepseek-v3-turbo |
| Input | $0.39 per M | $0.40 per M |
| Output | $0.39 per M | $1.30 per M |
| Context length | 131,072 tokens | 64,000 tokens |
| Accepts | image, 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.