External Model - Language Model - ChatGPT

🛠

Frontier Text Reasoning via OpenAI's GPT Models

Read, reason over, or write text inside a CNAPS Studio flow with OpenAI's GPT family — from gpt-5.5-pro for the hardest multi-step reasoning down to gpt-5 nano for fast, basic text tasks. Runs on OpenAI's servers via API.

🔑 Requires a OpenAI API key

Click to use ChatGPT on CNAPS Studio

What it does

This node connects your CNAPS Studio flows to OpenAI's GPT large language models through the OpenAI API. Use it whenever a flow needs a model to read, reason over, or write text — interpreting the output of a vision model, drafting or enhancing prompts for image/video generators, summarizing, translating, or restructuring data. Because these run on OpenAI's servers, you get frontier general-purpose reasoning without hosting a model locally.

Problem it solves

• Frontier reasoning without infrastructure — No local GPU or weights; the node calls OpenAI's hosted models directly.
• Full quality/cost spectrum in one node — Nine tiers from gpt-5.5-pro (deepest reasoning) through flagship gpt-5.5 down to gpt-5 nano (fastest, cheapest), plus a code-specialized gpt-5.2-codex — swap tiers without changing your flow.
• Glue between vision and generation nodes — Turn raw model output into readable reports, or expand simple text into detailed generation prompts

Which tier to pick

Reach for a *-pro tier for the hardest multi-step reasoning, math, and coding; gpt-5.5 as the balanced everyday default; and mini / nano when speed and cost matter more than depth on simple tasks.

Configuring the Node

Basic Settings

Model name

System prompt or instruction — Tell the model how to behave. Examples:

• "Summarize the detection results in 2-3 sentences."
• "Convert these labels into a product description."
• "Translate the following text to French."

Advanced Options

Maximum tokens to generate (default: 2048)

• Controls response length. Increase for longer outputs.

Sampling temperature (default: 0.7, range: 0.0–1.0)

• Lower (0.0–0.3): Focused, consistent responses
• Higher (0.7–1.0): Creative, varied responses

Use Cases

Direction 1: Vision Model → Language Model (Analysis)

Best when vision output is complex or needs interpretation.

Example: Scene Segmentation → Report

Input - Image → Scene Segmentation (MaskFormer) → Language Model → Output - Text Viewer

System prompt:

Convert this segmentation data into a structured scene report. Include: 1) Setting type, 2) People count, 3) Key objects detected, 4) Overall scene summary. Use plain language, not raw data.

Direction 2: Language Model → Image Generation (Prompt Enhancement)

Input - Text Input → Language Model → Image Generation (Z-Image-Turbo) → Output - Image Viewer

System prompt:

You are an expert image prompt engineer. Transform the user's simple description into a detailed, vivid prompt optimized for AI image generation. Include: subject details, setting/environment, lighting, artistic style, mood/atmosphere, and composition. Output only the enhanced prompt, nothing else.

How ChatGPT compares

ChatGPT is one of three external LLM options in CNAPS Studio:

Compliance & Provenance

For more on how we classify models and mark outputs, see our AI Policy.

Run it now

Click to use ChatGPT