deepseek-ai/DeepSeek-V3 vs Qwen: Qwen3.5-35B-A3B
They cost about the same for input tokens: deepseek-ai/DeepSeek-V3 $0.32 per M, Qwen: Qwen3.5-35B-A3B $0.3125 per M. deepseek-ai/DeepSeek-V3 is 1.4× cheaper for output tokens: deepseek-ai/DeepSeek-V3 costs $0.89 per M and Qwen: Qwen3.5-35B-A3B costs $1.25 per M. Qwen: Qwen3.5-35B-A3B reads more: deepseek-ai/DeepSeek-V3 takes up to 163,840 tokens of context and Qwen: Qwen3.5-35B-A3B up to 262,144. deepseek-ai/DeepSeek-V3 accepts text; Qwen: Qwen3.5-35B-A3B accepts image, text, video.
| deepseek-ai/DeepSeek-V3 | Qwen: Qwen3.5-35B-A3B | |
|---|---|---|
| Model id | deepseek-ai/DeepSeek-V3 | qwen/qwen3.5-35b-a3b |
| Input | $0.32 per M | $0.3125 per M |
| Output | $0.89 per M | $1.25 per M |
| Context length | 163,840 tokens | 262,144 tokens |
| Accepts | text | image, text, video |
| Produces | text | text |
| Served by | deepinfra | 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.