Skip to main content

Claude

This node uses Claude from Anthropic to generate text.

Processes inputs using Anthropic's Claude models, from the fast Haiku tier to the most capable Opus and Fable tiers. Claude 4.6 models support adaptive thinking with an effort control; Claude 4.5 models support extended thinking with a token budget.

Claude
System MessageText
Prompt*Text (multiline)
ContextText
ModelSelect
ThinkingToggle
Adaptive ThinkingToggle
EffortSelect
Budget TokensSlider
+ 1 more…
Fields marked * are required. Dots are connection handles.

Inputs

Each input can be typed in directly or connected to another node's output.

InputTypeRequiredDescription
System MessageTextOptionalOverride the default system instructions for the LLM (e.g. 'You are a concise assistant that responds only in bullet points.').
PromptText (multiline)RequiredEnter your text here
ContextTextOptionalAdditional context that will be used to answer your prompt.

Settings

SettingTypeDefaultDescriptionAvailable when
ModelSelectClaude 4.6 Sonnet
ThinkingToggleModel is “Claude 4.5 Opus”, “Claude 4.5 Sonnet”, “Claude 4.5 Haiku”
Adaptive ThinkingToggleOnRecommended for Claude 4.6 models. Enables adaptive thinking and interleaved thinking.Model is “Claude 4.6 Opus”, “Claude 4.6 Sonnet”
EffortSelectMedium (recommended for Sonnet 4.6)Controls adaptive thinking depth. Use medium for most Sonnet 4.6 tasks, high/max for harder Opus 4.6 and Fable 5 tasks.Model is “Claude 4.6 Opus”, “Claude 4.6 Sonnet”, “Claude Fable 5”
Budget TokensSlider1024Determines how many tokens Claude can use for its internal reasoning process. Larger budgets can enable more thorough analysis for complex problems, improving response quality. Range: 1024–63999.Model is “Claude 4.5 Opus”, “Claude 4.5 Sonnet”, “Claude 4.5 Haiku” and Thinking is on
TemperatureSlider1Use temperature closer to 0.0 for analytical tasks, and closer to 1.0 for creative tasks. Range: 0–1.

Model options

OptionDefault
Claude 4.5 Opus
Claude 4.5 Haiku
Claude 4.5 Sonnet
Claude 4.6 Opus
Claude 4.6 Sonnet
Claude Fable 5

Effort options

OptionDefault
Low
Medium (recommended for Sonnet 4.6)
High (default capability)
Max (highest Opus 4.6 capability)

Output

Type: Markdown text (markdown)