model | string | ✅ | - | Model ID used to generate the response. |
messages | array<object> | ✅ | - | A list of messages comprising the conversation so far. Depending on the model you use, different message types (modalities) are supported, like text, images, and audio. |
>messages.role | enum | ✅ | user assistant system developer | The role of the message sender. Can be user model. |
>messages.name | string | - | - | An optional name for the participant. Provides the model information to differentiate between participants of the same role. |
>messages.content | string|array<object> | ✅ | - | The contents of the developer message. |
>messages.content.type | string | - | text image_url | The type of the content part. |
>messages.content.text | string | - | - | The text content. |
>messages.content.image_url | object | - | - | The image URL content. |
>messages.content.image_url.url | string | - | - | The URL of the image. |
max_tokens | integer | - | - | An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and reasoning tokens. |
stream | boolean | - | - | Whether to stream the response back incrementally. Defaults to false. |