by DeepSeek
Thinking mode of DeepSeek-V3.1; DeepSeek V3.1 is a text generation model provided by DeepSeek, featuring a hybrid reasoning architecture that achieves an effective integration of thinking and non-thinking modes.
| Input | $0.56 / 1M tokens |
| Output | $1.68 / 1M tokens |
| Context window | 128,000 tokens |
| Modalities | text |
| Features | thinking, tools, function_calling, structured_outputs |
Use DeepSeek-V3.1-Think via the AIHubMix unified API — one interface for every major LLM.