📦 NEW: Provider - DeepSeek
We're excited to announce the addition of DeepSeek in the ever extending list of LLM providers on Langbase. You can now use the DeepSeek's latest models v3 and r1 on Langbase.
DeepSeek
Leverage the power of DeepSeek's latest models in Langbase. DeepSeek has recently launched a set of powerful and competitive LLMs which are open-source, promoting broad usability and innovation within the AI community. The models currently include:
-
deepseek-r1: DeepSeek R1 is a powerful reasoning model that achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. Before delivering the final answer, the model first generates a Chain of Thought (CoT) to enhance the accuracy of its responses. It directly competes with OpenAI's o1 models at a fraction of the cost.
-
deepseek-v3: A strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token from Deepseek. A very capable model, competing with other flagship models without costing as much.
See our models and providers documentation for more details on all the available models and their capabilities.