Side-by-side technical and economic comparison between Google's Gemini 3.1 Pro Preview and Alibaba / Qwen's Qwen 2.5 72B Instruct — Together AI.
• Qwen 2.5 72B Instruct — Together AI: Classified as a Legacy Reference model (Deprecated on Together AI (Reference)).
| Metric | Gemini 3.1 Pro Preview | Qwen 2.5 72B Instruct — Together AI | Advantage |
|---|---|---|---|
| Provider Organization | Alibaba / Qwen | — | |
| Standard Input / 1M | $2.00 | $0.35 | Qwen 2.5 72B Instruct — Together AI (83% lower) |
| Cached Input / 1M | $0.20 | $0.175 | Qwen 2.5 72B Instruct — Together AI lower |
| Output / 1M | $12.00 | $0.40 | Qwen 2.5 72B Instruct — Together AI lower |
| Context Window | 1.05M | 128k | Gemini 3.1 Pro Preview (1.05M) |
| Max Generation Tokens | 16.4k | 8.2k | Gemini 3.1 Pro Preview |
| Tokenizer Family | Google Gemini SentencePiece (256k vocabulary) | Qwen Byte-level BPE (~152k vocabulary) | — |
Opt for Gemini 3.1 Pro Preview when your engineering requirements prioritize Google's ecosystem, specific tokenizer efficiencies (Calibrated Gemini Tokenizer (±4%)), or when your expected prompt-to-completion ratios favor its $2/M input rate.
Opt for Qwen 2.5 72B Instruct — Together AI when looking for Alibaba / Qwen's tooling integration, specific context window depth (128k tokens), or when output generation volume favors its $0.4/M rate.