Models
One name per model, however many providers serve it.
MiniMax: MiniMax H3 Image Highspeed
Accepts- Text
- Image
Creates- Image
MiniMax H3 Image Highspeed is the faster version of MiniMax's H3 Image model.
minimax/minimax-h3-image-highspeedNov 11, 20264K contextUp to 10 images a requestEdits pictures3,561 Toman to 17,256 Toman an imageMiniMax: MiniMax H3 Image
Accepts- Text
- Image
Creates- Image
MiniMax H3 Image is MiniMax's image generation and editing model.
minimax/minimax-h3-imageNov 10, 20264K contextUp to 10 images a requestEdits pictures1,781 Toman to 8,628 Toman an imageMiniMax: MiniMax M3.1 Flash
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningMiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in complex agentic tasks, coding, and cybersecurity.
minimax/minimax-m3.1-flashOct 19, 20261M context54,656 Toman/M input tokens218,624 Toman/M output tokensMiniMax: Hailuo 3 Max
Accepts- Text
- Image
Creates- Video
MiniMax H3 Max is a video-generation model from MiniMax, jointly released with fal.ai.
minimax/hailuo-3-maxSep 2, 20265–15 s768p · 480pfrom 18,019 Toman/secondMiniMax: Hailuo 3
Accepts- Text
- Image
Creates- Video
MiniMax H3 is a lightweight, open-weights video generation model from MiniMax.
minimax/hailuo-3Jul 29, 20265–15 s2Kfrom 46,850 Toman/secondMiniMax: Speech 2.8 HD
Accepts- Text
Creates- Audio
MiniMax Speech 2.8 HD is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.
minimax/speech-2.8-hdJul 16, 202645 voicesMP336,039 Toman per 1,000 charactersMiniMax: Speech 2.8 Turbo
Accepts- Text
Creates- Audio
MiniMax Speech 2.8 Turbo is a text-to-speech model from MiniMax. It is suited for applications that generate spoken audio from text and accepts arbitrary MiniMax voice IDs.
minimax/speech-2.8-turboJul 16, 202645 voicesMP321,623 Toman per 1,000 charactersMiniMax: MiniMax M3
Accepts- Text
- Image
- Video
Creates- Text
ToolsJSONReasoningMiniMax-M3 is a multimodal foundation model from MiniMax.
minimax/minimax-m3May 31, 20261M context109,312 Toman/M input tokens433,832 Toman/M output tokensMiniMax: Hailuo 2.3
Accepts- Text
- Image
Creates- Video
Hailuo 2.3 is a video generation model from MiniMax. It accepts text prompts and reference images as input and generates video output, supporting both text-to-video and image-to-video workflows.
minimax/hailuo-2.3Apr 20, 20266–10 s1080pfrom 29,444 Toman/secondMiniMax: MiniMax M2.7
Accepts- Text
Creates- Text
ToolsReasoningMiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.
minimax/minimax-m2.7Mar 18, 2026197K context218,624 Toman/M input tokens649,040 Toman/M output tokensMiniMax: MiniMax M2.5
Accepts- Text
Creates- Text
ToolsJSONReasoningMiniMax-M2.5 is a SOTA large language model designed for real-world productivity.
minimax/minimax-m2.5Feb 12, 2026198K context99,064 Toman/M input tokens345,016 Toman/M output tokens
11 of 581 models · Catalog updated 3 hours ago. · Free plan prices, in Toman at today's rate. Plans and prices

