ERNIE-4.5-21B-A3B-Thinking vs DeepSeek R1 Distill Qwen3 8B 0528
DeepSeek R1 Distill Qwen3 8B 0528 is 1.2× cheaper for input tokens: ERNIE-4.5-21B-A3B-Thinking costs $0.07 per M and DeepSeek R1 Distill Qwen3 8B 0528 costs $0.06 per M. DeepSeek R1 Distill Qwen3 8B 0528 is 3.1× cheaper for output tokens: ERNIE-4.5-21B-A3B-Thinking costs $0.28 per M and DeepSeek R1 Distill Qwen3 8B 0528 costs $0.09 per M. About the same: ERNIE-4.5-21B-A3B-Thinking takes up to 131,072 tokens of context and DeepSeek R1 Distill Qwen3 8B 0528 up to 128,000.
| ERNIE-4.5-21B-A3B-Thinking | DeepSeek R1 Distill Qwen3 8B 0528 | |
|---|---|---|
| Model id | baidu/ernie-4.5-21B-a3b-thinking | deepseek/deepseek-r1-0528-qwen3-8b |
| Input | $0.07 per M | $0.06 per M |
| Output | $0.28 per M | $0.09 per M |
| Context length | 131,072 tokens | 128,000 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.