EdgazeDocsEdgaze Docs
DocumentationAPI Reference
Home
Core
Workflow InputWorkflow FormWorkflow OutputMergeMerge ObjectsTemplateMap
AI
LLM ChatLLM ImageLLM Embeddings
Logic & integration
HTTP RequestWeb ScrapeYouTube TranscriptJSON ParseConditionDelayLoopRun Another Workflow (Remix)

Platform status

Checking platform status
Block reference

LLM Chat

Run text through a language model for writing, reasoning, extraction, or transformation.

Audience

Creators building and publishing workflows.

Overview#

LLM Chat is the main text-generation block. It accepts upstream data plus instructions, runs a selected model, and returns a response for the next step.

Use it for rewriting, summarizing, classifying, analyzing, or any job that needs language understanding. The current catalog default is gpt-5.6-terra.

LLM Chat

Press enter or space to select a node. Press delete to remove it and escape to cancel.
Press enter or space to select an edge. You can then press delete to remove it or escape to cancel.

Ports#

  • Input: Input: Connected upstream text or JSON-like content.
  • Output: Response: The model's generated text for downstream blocks.

Inspector#

  • Prompt: Instructions used when Input is not connected, or as guidance alongside connected data.
  • Style / System (optional): Tone, role, and constraints for the model.
  • Model: Choose among the current catalog options and trade off quality, cost, and speed. Match the provider requirements for the listing's credential mode.
  • Max Tokens: Cap on response length; align it with what the product should return.
  • Stream and Safe Mode: Inline toggles for live streaming and safer defaults.

Tips#

  • Give each LLM block one clear job instead of stacking many tasks in one prompt.
  • Feed raw data through Input; keep transformation instructions in the prompt.
  • Use a stronger model for nuanced writing; lighter models for fast utility work.
  • Set max tokens close to the expected answer length to avoid waste.

Related#

  • Workflow Studio

Was this useful?

Your response helps us improve the documentation.

More blocks

Workflow Input

Ask the customer one clear question and turn their answer into data your workflow can use.

Workflow Form

Collect several run-modal fields in one grouped form, each with a stable key for downstream steps.

Workflow Output

Define what the customer receives when the workflow finishes.

On this page
OverviewPortsInspectorTipsRelated
© 2026 Edge Platforms, Inc. All rights reserved.