Phosor

MiniMax H3 / MiniMax H3 Turbo

MiniMax H3.AI video creation.

An idea. An image. A world of references. Turn your starting point into video with MiniMax H3 on Phosor.

Browse freely. Sign in to generate. Pay per use.

Concept artwork

Limits & formats

Text, image and reference inputs, with native audio generation. Choose MiniMax H3 or MiniMax H3 Turbo in each mode.

CapabilitySupported
Video output4–15 seconds · 24 fps · MP4
Resolution480p or 768p; landscape 16:9 outputs are 832×480 or 1344×768
Aspect ratios16:9 · 4:3 · 1:1 · 3:4 · 9:16
Image to videoStarting image required; ending image optional
Reference imagesUp to 9 with images only; up to 5 when combined with video or audio
Image dimensionsLongest edge ≤2048px; aspect ratio ≤4:1 in either orientation
Reference videosUp to 3; combined duration ≤15.1s; frame rate ≤24 fps
Reference audioUp to 3 clips; each ≤10s; requires an image or video reference
Image upload formatsJPEG · PNG · WebP; published default maximum 20 MiB per image
Video upload formatsMP4 · WebM · MOV
Audio upload formatsMP3 · WAV · OGG · M4A · AAC · FLAC

Reference counts are per type and cannot necessarily all be combined at their maximums. Files must be readable with supported codecs. Current service limits apply.

Performance

768p · 15-second output · Reference to video. Observed completion times; shorter bars mean less waiting.

9 reference images
MiniMax H33326–3467 s ≈ 55.4–57.8 min

6 completed runs

MiniMax H3 Turbo392–414 s ≈ 6.5–6.9 min

3 completed runs · median 411 s

5 images + 3 videos + 3 audio clips
MiniMax H33402–4006 s ≈ 56.7–66.8 min

7 completed runs

MiniMax H3 Turbo379–481 s ≈ 6.3–8.0 min

3 completed runs · median 421 s

Historical Phosor production tests: H3, September 2026; Turbo, October 2026. Turbo results use prewarmed models with face enhancement off. Times include request processing and transfers, not just inference. Different test batches; ranges describe these runs and may vary with inputs, loading and queue time.

01 / Start creating

Bring your idea into the frame.

Choose the input that fits your shot. Each mode is available in MiniMax H3 and MiniMax H3 Turbo.

03

Reference to video

Bring subjects, places and movement together. Tell H3 how to use each reference.

What you need

A prompt and at least one reference image or video. Audio references are optional; audio alone is not enough.

02 / For developers

The same H3. In your workflow.

Use the exact model ID from the playground. Submit a request, check its status and retrieve the finished video.

  1. 01Create an API key
  2. 02Submit a request
  3. 03Check status
  4. 04Retrieve the result
Text to video · MiniMax H3cURL
curl -X POST https://phosor.ai/api/v1/inference/submit \
  -H "X-API-Key: $PHOSOR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "minimax/h3/text-to-video",
  "prompt": "A hiker walks along a snowy ridge at sunrise. A slow tracking shot follows from behind.",
  "duration": 5,
  "resolution_tier": "480p",
  "aspect_ratio": "16:9"
}'

Set PHOSOR_API_KEY to your own API key. This example submits a 5-second, 480p request; generation is billed.

03 / Good to know

Before your first shot.

Can I use H3 without writing code?

Yes. Open a model page and sign in to create in the playground. The same models are available through the Phosor API.

Which mode supports first and last frames?

Image to video. Provide a starting image with image_url and optionally an ending image with end_image_url.

How much does H3 cost?

H3 is billed per output video second. Resolution and MiniMax H3 or MiniMax H3 Turbo determine the rate; reference images and videos may add charges. The pricing page lists current output and input rates.

Where can I check reference limits?

Review current counts, upload limits and supported formats in the playground and API documentation before submitting.

MiniMax H3 / Phosor

Your next scene starts here.

Choose an input. Shape the shot. Create with H3.

Try MiniMax H3