Macaron V1 Tall vs Qwen: Qwen3.5-122B-A10B
Macaron V1 Tall is 1.2× cheaper for input tokens: Macaron V1 Tall costs $0.2475 per M and Qwen: Qwen3.5-122B-A10B costs $0.29 per M. Macaron V1 Tall is 1.7× cheaper for output tokens: Macaron V1 Tall costs $1.43 per M and Qwen: Qwen3.5-122B-A10B costs $2.40 per M. Both read up to 262,144 tokens of context. Macaron V1 Tall accepts text; Qwen: Qwen3.5-122B-A10B accepts image, text, video.
| Macaron V1 Tall | Qwen: Qwen3.5-122B-A10B | |
|---|---|---|
| Model id | mindai/macaron-v1-tall | qwen/qwen3.5-122b-a10b |
| Input | $0.2475 per M | $0.29 per M |
| Output | $1.43 per M | $2.40 per M |
| Context length | 262,144 tokens | 262,144 tokens |
| Accepts | text | image, text, video |
| Produces | text | text |
| Served by | novita | alibaba |
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.