Claude Chat

Provided by AnthropicLearn More

Leverage Claude's exceptional reasoning and analysis capabilities for complex tasks. Supports system prompts, attachments, and precise parameter tuning. Excels at long-form content, analysis, and coding tasks.

Preview

Inputs

Prompt
text
The main prompt or question to send to the language model.
Model
dropdown
The model to use for the language model.
default: claude-sonnet-4-5Accepts: claude-sonnet-4-5, claude-sonnet-4-0, claude-3-7-sonnet-latest, claude-3-5-sonnet-latest, claude-3-5-haiku-latest, claude-opus-4-1, claude-opus-4-0
System Prompt
text
Initial prompt that helps set the behavior and context for the model.
optional: true
Attachments
generic
Accepts multiple
Additional context or documents to be included with the prompt.
optional: true
Last Message Only
toggle
Only use the last message in the conversation for generation, ignoring the previous conversation and messages.
default: false
Temperature
number
Controls randomness in the output. Lower values (near 0) make the output more focused and deterministic, while higher values make it more creative and random.
optional: trueminimum: -1maximum: 1
Seed
seed
The seed to use for the model.
default: 2262
Top P
number
Nucleus sampling parameter between 0 and 1. Lower values (e.g. 0.1) limit responses to only the most likely tokens. Use either this or temperature, not both.
optional: true
Top K
number
Limits the model to only sample from the top K options for each token. Used to remove low probability responses.
optional: true
Max Tokens
number
Maximum number of tokens to generate.
optional: true
Stop Sequences
text
Accepts multiple
Array of text sequences that will cause the model to stop generating further text when encountered.
optional: true
Presence Penalty
number
Penalizes the model for repeating information already present in the prompt. Higher values reduce repetition.
optional: trueminimum: -2maximum: 2
Frequency Penalty
number
Penalizes the model for repeatedly using the same words or phrases. Higher values encourage more diverse word choice.
optional: trueminimum: -2maximum: 2

Outputs

Response
text
The most recent text response generated by the language model.