openai — LLM AI Model
ChatGPT turns a prompt into text for summarizing, translating, drafting, and reading code, with the system prompt, temperature and length all under your control. Billed to your own OpenAI account.
What it does
ChatGPT calls OpenAI's hosted GPT models: the text on the node's input port and the instruction you set are sent to OpenAI's API, and the generated text comes back on the output port. Nothing runs locally, and the tokens are billed to your own OpenAI account.
It is the general-purpose text step in a flow - summarising, translating, drafting, restructuring data, or reading code. The tiers trade cost against depth, and the cheapest is enough for reformatting; the flagship earns its price only where a harder task actually fails on the others.
When to use it
- Summarising or translating text that an earlier node produced
- Drafting and rewriting copy in the middle of an automated flow
- Turning loose notes or labels into structured, consistent output
- Reading code or logs and explaining in plain words what they say
Details
- CategoryLLM
- Year2026
- LicenseOpenAI Commercial Terms
Compliance & Provenance
- ProviderOpenAI · GPAI
- EU AI Act RiskLimited Risk
- Art. 50 TransparencyRequired — AI-generated outputs are marked
Inputs & Outputs
- Text InputInputstring
Input text to process
- Generated TextOutputstring
LLM generated output
Parameters
- modelstringdefault GPT-5.6 Terraoptions: GPT-5.6 Sol, GPT-5.6 Terra, GPT-5.6 Luna, GPT-5.5, +8 more
Model variant
Which OpenAI model to call. GPT-5.6 Sol = flagship for complex professional work. GPT-5.6 Terra (default) = balances intelligence and cost. GPT-5.6 Luna = optimized for cost-sensitive workloads. All three carry a ~1.05M-token context. The GPT-5.2 / 5.4 / 5.5 entries are the previous generation. GPT-5 Mini and GPT-5 Nano are on OpenAI's retirement list for 2026-12-11 — do not pick them for new flows; Terra and Luna are their named replacements. Pick by task difficulty, not by recency.
- promptstringdefault
System prompt / instruction
Optional system prompt that frames the task (role, style, constraints). The user message comes from the text input pin.
- max_tokensintegerdefault 2048range 1–8192advanced
Max tokens (1-8192)
Maximum tokens for the response. Default 2048. Lower to constrain length / cost; raise up to 8192 for long-form.
- temperaturefloatdefault 1range 0–2advanced
Temperature (0-2)
Sampling temperature. 0 = deterministic (best for factual / coding). 1.0 (default) = standard. >1 = creative.
Limitations
- Text in, text out. This node has one text input port - images, audio and files cannot reach it.
- Up to 8192 tokens per response, which bounds how long a single answer can be.
- Runs on your own OpenAI API key. Without one configured in the workspace the node cannot run.