A fast, chat-based, Mixture-of-Experts (MoE) model from DeepSeek.
The company that provides the model
The number of tokens you can send in a prompt
The maximum number of tokens a model can generate in one request
The cost of prompt tokens sent to the model
The cost of output tokens generated by the model
When the model's knowledge ends
When the model was launched
Capability for the model to use external tools
Ability to process and analyze visual inputs, like images
Support for multiple languages
Whether the model supports fine-tuning on custom datasets
DeepSeek V3 has a cost structure of $0.14 per million input tokens and $0.28 per million output tokens.
The API cost for DeepSeek V3 is $0.14 per million input tokens and $0.28 per million output tokens.
For DeepSeek V3, the price is $0.00014 per 1,000 input tokens and $0.00028 per 1,000 output tokens.
DeepSeek V3 supports a context window of up to 64,000 tokens.
DeepSeek V3 can generate up to 8,000 tokens in a single output.
DeepSeek V3 was released on December 26, 2024.
The knowledge cut-off date for DeepSeek V3 is July 1, 2024.
No, DeepSeek V3 does not support vision capabilities.
No, DeepSeek V3 does not support tool calling (functions).
Yes, DeepSeek V3 supports multiple languages, allowing it to handle input and output in several languages.
Yes, DeepSeek V3 supports fine-tuning on custom datasets.
You can find the official documentation for DeepSeek V3 here.
PromptHub is better way to test, manage, and deploy prompts for your AI products
