ComfyUI Node
BYOKey LLM (OpenAI Compatible)
Generate text responses from an OpenAI-compatible chat model. Supports image context when images are connected.
BYOKey LLM (OpenAI Compatible)
- images
- output_text
◄api_key►
◄base_urlhttps://api.openai.com/v1►
◄modelgpt-5►
◄prompt►
◄instructions►
◄temperature1.00►
◄top_p1.00►
◄max_tokens4096►
◄seed0►
Categoryapi/byokey/text
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | Your API key (sent as 'Authorization: Bearer <key>'). | |
| base_url | STRING | https://api.openai.com/v1 | API base URL. Override for OpenAI-compatible relays (e.g. DeepSeek, Qwen). '/chat/completions' is appended. |
| model | STRING | gpt-5 | The model used to generate the response. Common OpenAI ids: gpt-5.5-pro, gpt-5.5, gpt-5, gpt-5-mini, gpt-5-nano, gpt-4.1, gpt-4.1-mini, gpt-4.1-nano, o4-mini, o3, o1-pro, o1 |
| prompt | STRING | Text inputs to the model, used to generate a response. | |
| imagesopt | IMAGE | Optional image(s) to use as context for the model. To include multiple images, use the Batch Images node. | |
| instructionsopt | STRING | System instructions for the model on how to generate the response (sent as the 'system' message). | |
| temperatureopt | FLOAT | 1.000–2 | Controls randomness in the response (0.0-2.0). |
| top_popt | FLOAT | 1.000–1 | Controls diversity via nucleus sampling (0.0-1.0). |
| max_tokensopt | INT | 409616–16384 | Upper bound for the number of tokens generated for a response. |
| seedopt | INT | 00–2147483647 | Sampling seed (best-effort; not honored by all backends). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| output_text | STRING | — |