MiniMax H3 API

About MiniMax H3

MiniMax H3 turns a sentence, a still image or a few reference photos into a 4-to-15-second video with sound, up to 2K.

Call it with the model name minimax/h3/text-to-video on POST /jobs/createTask, from 28 credits for a 5-second clip ($0.28). New accounts get 30 free credits to try it in the Playground first.

Introduction

MiniMax H3 Text to video generates a clip from a prompt alone, with no image or reference set involved. You choose a length of 5 to 15 whole seconds, a resolution of 768p or 2k, and one of six aspect ratios, and the clip comes back with sound generated in the same pass. The prompt field takes up to 7,000 characters, enough for a full shot description rather than a caption.

Choose a MiniMax H3 mode by starting material

Key features

Six frame shapes, set per request

aspect_ratio accepts 16:9 (the default), 9:16, 1:1, 4:3, 3:4 and 21:9. The 21:9 value renders an anamorphic letterbox, which is how the published noir-window example was made: a red neon pulse, Venetian blind shadows and a slow head turn, all composed for the wide frame from one paragraph. Pick the shape before writing, so the brief places the subject for that frame.

Sound directed in the same brief

Audio is generated with the picture rather than dubbed on afterwards, so the prompt is also where the soundtrack is written: room tone, foley, music or a spoken line. In the thunder-wheat-field example the thunder arrives in the same file as the lightning, so it lands against the strikes instead of having to be cut to them in the edit.

768p and 2k, both native

Both resolutions are native outputs, and 480p and 720p are not options: the schema rejects them. The endpoint takes no seed, so that final run is a new take of the same brief rather than a sharper copy of the draft.

Request parameters

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

Each task is rounded up to whole credits, so one run at the lowest tier costs 28 credits for a 5-second clip ($0.28).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

Start a shot from nothing but an idea

Text-to-video is the H3 endpoint that needs no image input. The curtain-silhouette example shows the kind of brief that holds up best across re-runs: a static camera, a gauzy curtain, one warm lamp behind it and a silhouette whose outline is all that reads. The fewer details a brief leaves open, the closer consecutive takes stay to each other.

Test a lighting or timing idea

Light that changes over time is written entirely in the prompt. The thunder-wheat-field brief asks for intermittent reveal, a soaked shirt printed white by each strike and dropped back into darkness, across six seconds at 768p in 16:9. Short drafts like this show whether an effect reads before you spend a 2k run on it.

Open a sequence that continues elsewhere

H3 has no edit endpoint, and one request tops out at 15 seconds. For a longer scene, generate the first shot here, then continue it with MiniMax H3 Video extend: it opens the next shot on the final frame of the approved clip and returns the two joined in one file. When the subject must look exactly as designed, switch to image-to-video instead, because prose leaves wardrobe, body and framing to the model and consecutive runs drift.

Prompt guide & pro tips

Write the shot in the order it happens

Structure the prompt as subject, action, camera, light and sound. The noir-window prompt is a workable template: who is on the windowsill and what she wears, what she does (exhales smoke, turns her head slowly toward camera), then the look (blind shadows, deep blacks, 1970s grain) and finally the sound (rain and distant traffic).

Give two subjects one camera move

When a frame has to hold two things at once, give the camera a single move that serves both. The mirror-two-views example keeps a woman's back and her reflection in an antique mirror readable together by asking for a slow arc to the right. The same prompt states plainly that the garments stay on and nothing is removed; when a shot depends on wardrobe staying in place, write that out instead of leaving it implied.

Change one variable between runs

Because there is no seed, two runs with identical settings return two different takes. Keep the wording fixed while comparing takes, and when a take misses, change one element, such as the camera instruction or the lighting line, rather than rewriting the whole brief. If subject and framing must stay identical across takes, pin them with an opening frame on image-to-video instead.

API quick start

Call the MiniMax H3 API in three steps

1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
2. Send the request. POST /jobs/createTask with model minimax/h3/text-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.

# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "minimax/h3/text-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "aspect_ratio": "16:9",
    "resolution": "768p",
    "duration_seconds": 5
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

MiniMax H3 API questions

All MiniMax models

MiniMax H3 Max is the fast-generation variant, with an optional closing frame but no reference mode and no 2K. H3 is the all-rounder.

• MiniMax H3 APIExpressive clips with audio, up to 2KFrom 28 credits for a 5-second clip
• MiniMax Speech 2.8 HD APIHigh-fidelity speech in 400+ voices with emotion controlFrom 18 credits per 1,000 characters
• MiniMax Music 3.0 APIFinished stereo songs, with vocals or instrumentalFrom 27 credits per run
• MiniMax H3 Singularity LoRA APICommunity-tuned H3 video that loads your own LoRAsFrom 45 credits for a 5-second clip
• MiniMax H3 Max APIFast clips with ambience, effects and musicFrom 38 credits for a 5-second clip
• MiniMax H3 LoRA APIMiniMax H3 video with sound and up to three of your LoRAsFrom 38 credits for a 5-second clip
• MiniMax H3 Image LoRA APIH3 stills and edits with up to three of your LoRAsFrom 7 credits per image
• MiniMax Speech 2.8 Turbo APIFast speech in 400+ voices with emotion controlFrom 11 credits per 1,000 characters

Other video APIs

• Seedance 2.5 APIByteDance's newest: 30-second clips with native audioFrom 56 credits for a 5-second clip
• Kling 3.0 API4K clips, multi-shot cuts and motion controlFrom 51 credits for a 5-second clip
• Vidu Q4 Preview APIUp to 4K clips with sound and spoken dialogueFrom 34 credits for a 5-second clip
• Wan 3.0 APIUp to 30-second clips with synced audioFrom 34 credits for a 5-second clip
• Kling O3 APIKling’s unified model: create, animate, reference and edit up to 4KFrom 51 credits for a 5-second clip
• LTX 2.5 APILong 20-second takes up to 4K with a soundtrackFrom 68 credits for a 5-second clip

More about MiniMax H3

Try it

MiniMax H3 AI Video Generator onlineCreate videos with MiniMax H3 in PopNow

Compare

Kling 3.0 vs MiniMax H3

Docs

MiniMax H3 model ID and input schema in the API docsPopNow API quickstart: your first request in five minutesImage to video guide for the PopNow APIWebhooks: get MiniMax H3 results without polling