ComfyUI Node
BYOKey Gemini (Google)
Generate text responses with Google's Gemini models. Provide a prompt and, optionally, image(s) as multimodal context. Calls the Gemini Developer API directly with your own key.
BYOKey Gemini (Google)
- images
- STRING
◄api_key►
◄base_urlhttps://generativelanguage.googleapis.com/v1beta►
◄prompt►
◄modelgemini-2.5-flash►
◄seed42►
◄system_prompt►
◄temperature1.00►
◄top_p0.95►
◄max_output_tokens32768►
Categoryapi/byokey/text
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | Google AI Studio (Gemini) API key. | |
| base_url | STRING | https://generativelanguage.googleapis.com/v1beta | API base URL. Change only for third-party relays. |
| prompt | STRING | Text input to the model. Include detailed instructions, questions, or context for generating a response. | |
| model | COMBO | gemini-2.5-flash | 6 options: gemini-2.5-pro, gemini-2.5-flash, gemini-2.5-pro-preview-05-06, gemini-2.5-flash-preview-04-17, gemini-2.5-flash-lite, gemini-2.0-flash |
| seed | INT | 420–18446744073709550000 | Best-effort deterministic seed. By default a random seed is used. |
| imagesopt | IMAGE | Optional image(s) as context. Use the Batch Images node for multiple. | |
| system_promptopt | STRING | Foundational instructions that dictate the model's behavior. | |
| temperatureopt | FLOAT | 1.000–2 | Controls randomness. Lower is more deterministic, higher more creative. |
| top_popt | FLOAT | 0.950–1 | Nucleus sampling threshold. |
| max_output_tokensopt | INT | 3276816–65536 | Maximum tokens to generate, including internal thinking. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| STRING | STRING | — |