aichat_create_conversation
Ask an AI model a question and receive its generated answer, while optionally passing a conversation ID to continue prior context. Works with models like GPT, DeepSeek, Grok, and GLM.
Instructions
Create an AI conversation using the AiChat API.
Sends a question to the specified AI model and returns the generated answer.
Supports a wide range of models including GPT-4, GPT-5, o-series, DeepSeek, Grok, and GLM.
Use this when:
- You need to ask a question to an AI model
- You want to continue an existing conversation (provide conversation_id)
- You need answers from specific AI models like DeepSeek, Grok, or GLM
Returns:
JSON response containing the conversation ID and the generated answer.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | No | The model to use for generating the answer. Options include gpt-4.1, gpt-4o, gpt-5, o1, o3, o4-mini, deepseek-r1, deepseek-v3, grok-3, glm-4.7, and many more. Default is gpt-4.1. | gpt-4.1 |
| preset | No | An optional preset model configuration to apply for this conversation. | |
| question | Yes | The prompt or question to be answered by the AI model. Required. | |
| stateful | No | Whether to use stateful conversation mode. When True, the server tracks conversation history. Default is False (stateless). | |
| references | No | Optional list of reference sources or context to include when generating the answer. | |
| conversation_id | No | The unique identifier of an existing conversation to continue. If provided, the AI will respond in the context of the prior conversation. Leave empty to start a new conversation. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |