费用预估
| 语言模型 | 输入 (元 / M tokens) | 输出 (元 / M tokens) |
|---|---|---|
| Qwen/QVQ-72B-Preview | 12 | 36 |
| Qwen/Qwen2-VL-72B-Instruct | 16 | 48 |
| Qwen/Qwen2.5-72B-Instruct-128K | 5.37 | 5.37 |
| Qwen/Qwen2.5-Coder-32B-Instruct | 2 | 6 |
| Qwen/Qwen2.5-VL-72B-Instruct | 16 | 48 |
| Qwen/QwQ-32B | 2 | 6 |
| Qwen/Qwen-max | 2.4 | 9.6 |
| Qwen/Qwen-max-latest | 2.4 | 9.6 |
| Qwen/Qwen-plus | 0.8 | 2 |
| Qwen/Qwen-plus-latest | 0.8 | 16 |
| Qwen/Qwen-turbo | 0.3 | 0.6 |
| Qwen/Qwen-turbo-latest | 0.3 | 6 |
| Qwen/Qwen2.5-7B-instruct | 0.5 | 1 |
| Qwen/Qwen2.5-3B-instruct | 0.3 | 0.9 |
| Qwen/Qwen2.5-14B-Instruct | 1 | 3 |
| Qwen/Qwen2.5-32B-Instruct | 2 | 6 |
| Qwen/Qwen2.5-72B-Instruct | 4 | 12 |
| Qwen/Qwen3-235B-A22B | 2 | 20 |
| Qwen/Qwen3-30B-A3B | 0.75 | 7.5 |
| Qwen/Qwen3-32B | 2 | 20 |
| Qwen/Qwen3-14B | 1 | 10 |
| Qwen/Qwen3-8B | 0.5 | 5 |
| Qwen/Qwen3-4B | 0.3 | 3 |
| deepseek-ai/DeepSeek-R1 | 4 | 16 |
| deepseek-ai/DeepSeek-V3 | 2 | 8 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-14B | 1 | 3 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-32B | 2 | 6 |
| deepseek-ai/DeepSeek-R1-Distill-Qwen-7B | 0.5 | 1 |
| deepseek-ai/DeepSeek-V2.5 | 1.73 | 1.73 |
| BAAI/bge-reranker-v2-m3 | 0.09 | / |
| BAAI/bge-m3 | 0.09 | / |