google/gemini-3.1-pro vs Qwen: Qwen3.8 Max (0902)
They cost about the same for input tokens: google/gemini-3.1-pro $2.00 per M, Qwen: Qwen3.8 Max (0902) $2.00 per M. Qwen: Qwen3.8 Max (0902) is 2× cheaper for output tokens: google/gemini-3.1-pro costs $12.00 per M and Qwen: Qwen3.8 Max (0902) costs $6.00 per M. Both read up to 1,000,000 tokens of context. google/gemini-3.1-pro accepts image, text; Qwen: Qwen3.8 Max (0902) accepts image, text, video.
| google/gemini-3.1-pro | Qwen: Qwen3.8 Max (0902) | |
|---|---|---|
| Model id | google/gemini-3.1-pro | qwen/qwen3.8-max-0902 |
| Input | $2.00 per M | $2.00 per M |
| Output | $12.00 per M | $6.00 per M |
| Context length | 1,000,000 tokens | 1,000,000 tokens |
| Accepts | image, 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.