MiniMax API v1 updates:

  • Video generation now supports 15 models across 3 families:
    • Hailuo: T2V-01, I2V-01, I2V-01-Director, I2V-01-live, S2V-01, T2V-02, I2V-02, T2V-2.3, I2V-2.3, I2V-2.3-Fast
    • Veo: Veo-3.1, Veo-3.1-Fast, Veo-3.1-S2V, Veo-3.1-S2V-Fast
    • Sora: Sora-2
  • Image generation now supports 7 models: image-01, Midjourney V7, Midjourney NiJi 7, Nano Banana Pro, GPT Image 1.5, Seedream 4.5, Seedream 5.0

Example 1: Sora-2 9:16 image-to-video via POST /videos/create

fileID:

curl --location 'https://api.useapi.net/v1/minimax/videos/create' \
--header 'Authorization: Bearer user:12345-…' \
--form 'model="Sora-2"' \
--form 'options="720p-12sec"' \
--form 'prompt="Beast vs. Man"' \
--form 'aspectRatio="9:16"' \
--form 'fileID="user:1245-minimax:…-file:…"'

Result

Example 2: Midjourney V7 4:3 multi-reference image via POST /images/create

referenceFileId1:

referenceFileId2:

curl --location 'https://api.useapi.net/v1/minimax/images/create' \
--header 'Authorization: Bearer user:12345-…' \
--form 'model="midjourney-v7"' \
--form 'prompt="Looking straight at the camera the two princesses having a pleasant conversation at a café in Paris with the Eiffel Tower view in the background."' \
--form 'aspectRatio="4:3"' \
--form 'referenceFileId1="user:…-minimax:…-file:…"' \
--form 'referenceFileId2="user:…-minimax:…-file:…"'

Result: