Google family
# Gemini 3.6 Flash ## Overview GA Gemini Flash model for coding, multimodal reasoning, knowledge work, and multi-step workflows. ## Model Metadata - Provider: vertex - Category: text - Output Type: text - Slug: gemini-3-6-flash-vertex ## Notes Use the Playground tab above to test prompts and parameters.
Model input reference derived from preset schema.
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| seed | integer | No | null | Optional best-effort seed for repeatable output. |
| audio | audio | No | null | Optional audio for transcription or multimodal analysis. |
| images | image | No | [] | Optional images for multimodal understanding. |
| prompt | string | Yes | null | The instruction or question to send to the model. |
| videos | video | No | [] | Optional videos for multimodal understanding. |
| max_tokens | integer | No | 8192 | Maximum number of tokens the model may generate. |
| system_prompt | string | No | null | Optional instructions that define the model's role and response rules. |
| thinking_level | select | No | "MEDIUM" | Controls the reasoning depth, latency, and token usage. |
| media_resolution | select | No | "MEDIUM" | Controls the detail and token usage for image and video inputs. |