DeepSeek V3 in Tavory Workspace

Tavory's live catalog currently lists DeepSeek V3 from Deepinfra. The catalog describes it as deepseek-v3, a strong mixture-of-experts (moe) language model with 671b total parameters with 37b activated for each token. to achieve efficient inference and cost-effective training, deepseek-v3 adopts multi-head latent attention (mla) and deepseekmoe architectures.. Availability, plan access and provider pricing can change and are checked again when a request is sent.

The Tavory catalog describes DeepSeek V3 as useful for text and chat.

If DeepSeek V3 is available for your plan and route at send time, you can open a Tavory chat with this model preselected. Tavory is not the manufacturer of DeepSeek V3.