ERNIE 4.5 300B A47B vs Qwen3 Omni 30B A3B Thinking
Qwen3 Omni 30B A3B Thinking is 1.1× cheaper for input tokens: ERNIE 4.5 300B A47B costs $0.28 per M and Qwen3 Omni 30B A3B Thinking costs $0.25 per M. Qwen3 Omni 30B A3B Thinking is 1.1× cheaper for output tokens: ERNIE 4.5 300B A47B costs $1.10 per M and Qwen3 Omni 30B A3B Thinking costs $0.97 per M. ERNIE 4.5 300B A47B reads more: ERNIE 4.5 300B A47B takes up to 123,000 tokens of context and Qwen3 Omni 30B A3B Thinking up to 65,536. ERNIE 4.5 300B A47B accepts text; Qwen3 Omni 30B A3B Thinking accepts audio, image, text.
| ERNIE 4.5 300B A47B | Qwen3 Omni 30B A3B Thinking | |
|---|---|---|
| Model id | baidu/ernie-4.5-300b-a47b-paddle | qwen/qwen3-omni-30b-a3b-thinking |
| Input | $0.28 per M | $0.25 per M |
| Output | $1.10 per M | $0.97 per M |
| Context length | 123,000 tokens | 65,536 tokens |
| Accepts | text | audio, image, 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.