Side-by-side technical and economic comparison between DeepSeek's DeepSeek-V3 (Legacy API Alias) and Alibaba / Qwen's Qwen3 235B-A22B.
• DeepSeek-V3 (Legacy API Alias): Classified as a Legacy Reference model (Legacy Reference (API Aliased)).
| Metric | DeepSeek-V3 (Legacy API Alias) | Qwen3 235B-A22B | Advantage |
|---|---|---|---|
| Provider Organization | DeepSeek | Alibaba / Qwen | — |
| Standard Input / 1M | $0.14 | $0.90 | DeepSeek-V3 (Legacy API Alias) (84% lower) |
| Cached Input / 1M | $0.014 | $0.18 | DeepSeek-V3 (Legacy API Alias) lower |
| Output / 1M | $0.28 | $1.60 | DeepSeek-V3 (Legacy API Alias) lower |
| Context Window | 128k | 128k | Qwen3 235B-A22B (128k) |
| Max Generation Tokens | 8.2k | 32k | Qwen3 235B-A22B |
| Tokenizer Family | DeepSeek Byte-level BPE (~128k vocabulary) | Qwen SentencePiece BPE (152k vocabulary) | — |
Opt for DeepSeek-V3 (Legacy API Alias) when your engineering requirements prioritize DeepSeek's ecosystem, specific tokenizer efficiencies (Exact DeepSeek Tokenizer (±2%)), or when your expected prompt-to-completion ratios favor its $0.14/M input rate.
Opt for Qwen3 235B-A22B when looking for Alibaba / Qwen's tooling integration, specific context window depth (128k tokens), or when output generation volume favors its $1.6/M rate.