MiniMax
Developer toolsAPI key
MiniMax provides AI models for text, video, and audio. List models, generate responses, count tokens, generate and download videos, and create speech.
12 actions
| Action | Effect | Data handled | Scope |
|---|---|---|---|
| minimax_list_modelsList OpenAI-compatible MiniMax models available to the API key | read | General | |
| minimax_retrieve_modelRetrieve OpenAI-compatible metadata for one MiniMax model | read | General | |
| minimax_create_responseCreate a non-streaming MiniMax response using the OpenAI Responses API shape | write | Personal data | |
| minimax_estimate_input_tokensEstimate MiniMax response input tokens without invoking the model | write | General | |
| minimax_create_video_generation_v2Create a MiniMax H3 video generation task with text, image, video, or audio content | write | General | |
| minimax_text_to_videoCreate a MiniMax asynchronous text-to-video generation task | write | General | |
| minimax_image_to_videoCreate a MiniMax asynchronous image-to-video generation task from a first frame image | write | General | |
| minimax_query_video_generationQuery the status of a MiniMax video generation task and read its file id when it completes | read | General | |
| minimax_query_video_generation_v2Query a MiniMax H3 video generation task | read | General | |
| minimax_delete_video_generation_v2Delete a MiniMax H3 video generation task | destructive | General | |
| minimax_download_videoRetrieve the download URL and metadata for a generated MiniMax video file | read | General | |
| minimax_text_to_audioSynthesize text into audio with the MiniMax T2A v2 API | write | General |