MiniMax H3 Max Text to Video

minimax/h3-max/text-to-video

H3 Max by MiniMax - generate cinematic videos from text descriptions with AI. Create high-quality video content with natural motion, camera control, and optional audio generation.

Base price
$0.10USD / run
Execution
async
Model type
video
Input fields
6

Try the model

Playground

Open playground
Input
Text prompt for video generation
The aspect ratio of the generated image. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
The native generation resolution of the video. Allowed values: 480P, 768P.
515
The duration of the video in seconds. Range: 5 to 15.
Random seed. A random seed is selected when omitted.
How much effort to spend rewriting the prompt before generation. 'balanced' returns in about a second. 'quality' spends up to ~30s on a richer prompt.
OutputReady

Your output will appear here

Complete the inputs, then click Run.

Specifications

Pricing

Base price
$0.10 / run
Billing formula
(usage.duration ?? params.duration) * (params.resolution == "480P" ? 0.0125 : 0.02)

Context & modalities

Input
Schema-defined
Output
video

Capabilities

Chat
Not supported
Vision
Not supported
Reasoning
Not supported
Structured output
Not supported
Function calling
Not supported
Audio input
Not supported

Access

Provider
MiniMax
Model ID
minimax/h3-max/text-to-video
Execution
async
API
Unified Run API
Endpoint
/v1/run

API README

MiniMax H3 Max Text to Video

Generate cinematic videos directly from text with MiniMax H3 Max, a fal post-trained H3 variant optimized for stronger prompt adherence, visual quality, and inference throughput.

The endpoint supports 5–15 second video at 480P or 768P, ten aspect ratios, deterministic seeds, and balanced or quality prompt expansion.

Pricing

Current fal promotional rates are $0.0125 per second at 480P and $0.02 per second at 768P through September 7, 2026. Completed-task duration is used when available; otherwise the requested duration is used.

Technical Specs

  • Model ID: minimax/h3-max/text-to-video
  • Required input: prompt
  • Duration: 5–15 seconds; default 5
  • Resolution: 480P or 768P; default 768P
  • Aspect ratios: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16
  • Prompt expansion: balanced or quality
  • Output: downloadable video URL
  • Execution: asynchronous

Start building

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

Production API
Unified Run API endpoint
https://api.sandbase.ai/v1/run
Model ID
minimax/h3-max/text-to-video
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
  -X POST "https://api.sandbase.ai/v1/run" \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  --data-binary @- <<'SANDBASE_JSON'
{
  "model": "minimax/h3-max/text-to-video",
  "prompt": "A white kitten chases a butterfly across a sunlit garden. Gentle camera tracking, natural movement, soft afternoon light filtering through the leaves.",
  "duration": 5,
  "resolution": "768P",
  "prompt_expansion_mode": "balanced"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
  status=$(printf '%s' "$result" | jq -r .status)
  case "$status" in completed|failed|timeout) break ;; esac
  sleep 2
  result=$(curl --fail-with-body --silent \
    -H "Authorization: Bearer $SANDBASE_API_KEY" \
    "https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"

Choose your model

Compare models

All language models
ModelContextInput / 1MOutput / 1MReleased
MiniMax———Aug 26, 2026
MiniMax———Aug 31, 2026
MiniMax———Aug 26, 2026
MiniMax———Aug 14, 2026
MiniMax———Jul 29, 2026
MiniMax———Jul 29, 2026