A reasoning model developed by DeepSeek that enhances performance by generating a Chain of Thought (CoT) before delivering answers.
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 Reasoner (R1) has a cost structure of $0.55 per million input tokens and $2.19 per million output tokens.
The API cost for DeepSeek Reasoner (R1) is $0.55 per million input tokens and $2.19 per million output tokens.
For DeepSeek Reasoner (R1), the price is $0.00055 per 1,000 input tokens and $0.00219 per 1,000 output tokens.
DeepSeek Reasoner (R1) supports a context window of up to 64,000 tokens.
DeepSeek Reasoner (R1) can generate up to 8,000 tokens in a single output.
DeepSeek Reasoner (R1) was released on January 20, 2025.
The knowledge cut-off date for DeepSeek Reasoner (R1) has not been specified.
No, DeepSeek Reasoner (R1) does not support vision capabilities.
No, DeepSeek Reasoner (R1) does not support tool calling (functions).
Yes, DeepSeek Reasoner (R1) supports multiple languages, allowing it to handle input and output in several languages.
Yes, DeepSeek Reasoner (R1) supports fine-tuning on custom datasets.
You can find the official documentation for DeepSeek Reasoner (R1) here.
PromptHub is better way to test, manage, and deploy prompts for your AI products
