Chat → Complete
AI-generatedSummary
Send a sequence of messages to a VolcEngine ARK chat model to generate a chat completion response.
Inputs
- Model Source (required) — Choose the model by selecting from a predefined list or entering a custom model ID.
- Model (required) — Select a predefined VolcEngine ARK model when using 'From List' as the model source.
- Model ID (required) — Enter a custom model ID string when using 'Custom' as the model source.
- Messages (required) — Provide one or more messages with roles (system, user, assistant) and content to send as the chat input.
- Options — Optional parameters to control the generation such as temperature, top_p, max tokens, streaming, frequency and presence penalties, and stop sequences.
Output shape
An array of JSON objects each containing the response from the chat completion API for each input item.
Each output item pairs with its corresponding input item. The response JSON includes the full returned completion data as received from the VolcEngine ARK API's /chat/completions endpoint.
Examples
Example 1: Generate a chat response using a predefined model.
Set Model Source to 'From List', choose model, provide messages with roles and content, optionally adjust options like temperature and max tokens, then execute to receive the generated completion.
Example 2: Use a custom model ID for chat completion.
Set Model Source to 'Custom', enter the exact model ID string, supply chat messages, optionally configure generation options, and run to get the chat completion response.