{"items":[{"provider":"minimax","providerDisplayName":"MiniMax","providerDisplayDescription":"AI media generation — compose full songs (Music 3.0 / 2.6), generate images from text or a reference portrait (image-01 / image-01-live text-to-image and image-to-image), create video from text, a starting image, or reference footage (H3 up to 2K, and Hailuo-2.3), and turn text into lifelike speech (speech-2.8 / 2.6 / 02 voices).","endpoint":"/v1/t2a_v2","displayName":"MiniMax Text to Speech","displayDescription":"Turn text into lifelike speech with MiniMax speech-2.8 / 2.6 / 02 voices.","price":{"type":"PER_UNIT_MATRIX","amount":{"value":60,"currency":"USD"},"selectors":[{"label":"Model","key":"model","in":"body"}],"variants":[{"when":{"model":"speech-2.8-hd"},"price":{"type":"PER_UNIT","amount":{"value":100,"currency":"USD"},"per":1000000,"unit":"character"},"label":"speech-2.8-hd — $100 / M characters"},{"when":{"model":"speech-2.6-hd"},"price":{"type":"PER_UNIT","amount":{"value":100,"currency":"USD"},"per":1000000,"unit":"character"},"label":"speech-2.6-hd — $100 / M characters"},{"when":{"model":"speech-02-hd"},"price":{"type":"PER_UNIT","amount":{"value":100,"currency":"USD"},"per":1000000,"unit":"character"},"label":"speech-02-hd — $100 / M characters"},{"when":{"model":"speech-2.8-turbo"},"price":{"type":"PER_UNIT","amount":{"value":60,"currency":"USD"},"per":1000000,"unit":"character"},"label":"speech-2.8-turbo — $60 / M characters"},{"when":{"model":"speech-2.6-turbo"},"price":{"type":"PER_UNIT","amount":{"value":60,"currency":"USD"},"per":1000000,"unit":"character"},"label":"speech-2.6-turbo — $60 / M characters"},{"when":{"model":"speech-02-turbo"},"price":{"type":"PER_UNIT","amount":{"value":60,"currency":"USD"},"per":1000000,"unit":"character"},"label":"speech-02-turbo — $60 / M characters"}]},"tags":["verified"],"categories":["minimax","speech"]},{"provider":"minimax","providerDisplayName":"MiniMax","providerDisplayDescription":"AI media generation — compose full songs (Music 3.0 / 2.6), generate images from text or a reference portrait (image-01 / image-01-live text-to-image and image-to-image), create video from text, a starting image, or reference footage (H3 up to 2K, and Hailuo-2.3), and turn text into lifelike speech (speech-2.8 / 2.6 / 02 voices).","endpoint":"/v1/image_generation","displayName":"MiniMax Image (image-01 / image-01-live)","displayDescription":"Text-to-image and image-to-image with MiniMax (image-01 / image-01-live).","price":{"type":"PER_RESULT","amount":{"value":0.0035,"currency":"USD"}},"tags":["verified"],"categories":["image-generation","minimax"]},{"provider":"minimax","providerDisplayName":"MiniMax","providerDisplayDescription":"AI media generation — compose full songs (Music 3.0 / 2.6), generate images from text or a reference portrait (image-01 / image-01-live text-to-image and image-to-image), create video from text, a starting image, or reference footage (H3 up to 2K, and Hailuo-2.3), and turn text into lifelike speech (speech-2.8 / 2.6 / 02 voices).","endpoint":"/v1/video/minimax-hailuo-2.3","displayName":"MiniMax Video (Hailuo-2.3)","displayDescription":"Text-to-video and image-to-video with MiniMax Hailuo-2.3.","price":{"type":"PER_UNIT_MATRIX","amount":{"value":0.28,"currency":"USD"},"selectors":[{"label":"Model","key":"model","in":"body"},{"label":"Resolution","key":"resolution","in":"body"},{"label":"Duration (s)","key":"duration","in":"body"}],"variants":[{"when":{"model":"MiniMax-Hailuo-2.3","resolution":"768P","duration":6},"price":{"type":"PER_CALL","amount":{"value":0.28,"currency":"USD"}}},{"when":{"model":"MiniMax-Hailuo-2.3","resolution":"768P","duration":10},"price":{"type":"PER_CALL","amount":{"value":0.56,"currency":"USD"}}},{"when":{"model":"MiniMax-Hailuo-2.3","resolution":"1080P","duration":6},"price":{"type":"PER_CALL","amount":{"value":0.49,"currency":"USD"}}}]},"tags":["verified"],"categories":["minimax","video-generation"]},{"provider":"minimax","providerDisplayName":"MiniMax","providerDisplayDescription":"AI media generation — compose full songs (Music 3.0 / 2.6), generate images from text or a reference portrait (image-01 / image-01-live text-to-image and image-to-image), create video from text, a starting image, or reference footage (H3 up to 2K, and Hailuo-2.3), and turn text into lifelike speech (speech-2.8 / 2.6 / 02 voices).","endpoint":"/v1/music_generation","displayName":"MiniMax Music","displayDescription":"Text-to-music: turn a style prompt and lyrics into a full song (MiniMax Music 3.0 / 2.6).","price":{"type":"PER_UNIT_MATRIX","amount":{"value":0.15,"currency":"USD"},"selectors":[{"label":"Model","key":"model","in":"body"}],"variants":[{"when":{"model":"music-3.0"},"price":{"type":"PER_CALL","amount":{"value":0.15,"currency":"USD"}},"label":"music-3.0 — $0.15 / song"},{"when":{"model":"music-2.6"},"price":{"type":"PER_CALL","amount":{"value":0.15,"currency":"USD"}},"label":"music-2.6 — $0.15 / song"}]},"tags":["verified"],"categories":["minimax","music-generation"]},{"provider":"minimax","providerDisplayName":"MiniMax","providerDisplayDescription":"AI media generation — compose full songs (Music 3.0 / 2.6), generate images from text or a reference portrait (image-01 / image-01-live text-to-image and image-to-image), create video from text, a starting image, or reference footage (H3 up to 2K, and Hailuo-2.3), and turn text into lifelike speech (speech-2.8 / 2.6 / 02 voices).","endpoint":"/v1/video/minimax-h3","displayName":"MiniMax Video (H3)","displayDescription":"Text-to-video, image-to-video, and reference-to-video with MiniMax-H3, up to 2K.","price":{"type":"TIERED","amount":{"value":0,"currency":"USD"},"tiers":[{"label":"768P","when":{"resolution":"768P"},"selector":{"label":"768P","key":"task.usage.total_seconds","in":"output"},"price":{"type":"PER_UNIT","amount":{"value":0.08,"currency":"USD"},"per":1,"unit":"second"}},{"label":"2K","when":{"resolution":"2K"},"selector":{"label":"2K","key":"task.usage.total_seconds","in":"output"},"price":{"type":"PER_UNIT","amount":{"value":0.13,"currency":"USD"},"per":1,"unit":"second"}},{"label":"Input images","selector":{"label":"Input images","key":"task.usage.billable_input_images","in":"output"},"price":{"type":"PER_UNIT","amount":{"value":0.04,"currency":"USD"},"per":1,"unit":"image"}}]},"tags":["verified"],"categories":["minimax","video-generation"]}],"total":5}