Search
Chat with DeepSeek models. DeepSeek provides powerful language models with strong reasoning capabilities.
The message prompt to send to the model.
The DeepSeek model to use for chat completion.
A system prompt that sets the behavior and context for the conversation.
Attachments to include with the prompt (images, text, etc.).
If enabled, only the last message will be sent to the model instead of the full conversation history.
Controls randomness in the output. Higher values make the output more random, lower values make it more deterministic.
A seed value for reproducible outputs. Use the same seed to get consistent results.
Nucleus sampling parameter. Controls diversity via nucleus sampling.
Limits the number of highest probability tokens to consider.
Maximum number of tokens to generate in the response.
Sequences that will cause the model to stop generating further tokens.
Penalizes tokens based on whether they appear in the text so far.
Penalizes tokens based on their frequency in the text so far.
The last response from the model.