ComfyUI Node
OpenAI Text Generation
A ComfyUI node in ERPK/OpenAI with 11 inputs and 1 output.
OpenAI Text Generation
- client
- response
◄prompt►
◄seed-1►
◄modelgpt-5.6-sol►
◄temperature0.70►
◄max_tokens4096►
◄top_p1.00►
◄stop_sequences►
◄response_formatdefault►
◄reasoning_effortnone►
◄verbositydefault►
CategoryERPK/OpenAI
Inputs (11)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Text prompt for OpenAI | |
| seed | INT | -1-1–2147483647 | Seed for reproducible outputs (best-effort). Randomizes by default. |
| clientopt | OPENAI_API_CLIENT | OpenAI API client from OpenAI API Config node (optional if API key is configured in Settings) | |
| modelopt | COMBO | gpt-5.6-sol | OpenAI model to use for generation |
| temperatureopt | FLOAT | 0.700–2 | Creativity level (0.0=focused, 2.0=very creative) |
| max_tokensopt | INT | 4096256–16384 | Maximum length of response |
| top_popt | FLOAT | 1.000–1 | Nucleus sampling - cumulative probability threshold (1.0=disabled) |
| stop_sequencesopt | STRING | Stop generation at these sequences (one per line, leave empty to disable) | |
| response_formatopt | COMBO | default | Output format (use json_object for JSON mode) |
| reasoning_effortopt | COMBO | none | Reasoning depth for o-series and gpt-5.x reasoning models. Ignored by non-reasoning models. |
| verbosityopt | COMBO | default | Output verbosity for gpt-5.x models. 'low' produces terse responses, 'high' produces more detailed ones. Distinct from max_tokens — shapes style, not the hard length cap. 'default' lets the model choose. Silently ignored by older models that do not accept verbosity. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |