Models

DeepSeek V3.1 Fast Compare

Compare pricing, specifications, performance, and benchmarks for up to four models.

DeepSeekDeepSeek V3.1 Fast
DeepSeek logo
DeepSeek V3.1 Fast
DeepSeek · text → text

The model provider is the Sophon platform. DeepSeek V3.1 Fast is the high-TPS speed version of DeepSeek V3.1. Hybrid thinking mode: By modifying the chat template, a single model can simultaneously support both thinking and non-thinking modes. Smarter tool usage: Through post-training optimization, the model’s performance in tool utilization and agent tasks has improved significantly.

Input$1.096 /M
Output$3.288 /M

Pick a second model to start comparing.

Popular comparisons

Related model match-ups readers also look at.