minimax: MiniMax H3 Lite

A lightweight multimodal video generation model supporting text-to-video, first and last frame image-to-video, and reference-to-video generation at 480P and 768P.

cloudflareWorkersAI/minimax/h3-lite

A lightweight multimodal video generation model supporting text-to-video, first and last frame image-to-video, and reference-to-video generation at 480P and 768P.

Specifications & capabilities

Input
text, image, video, audio
Output
video
Capabilities
audioInput, multimodal, videoOutput, visionInput

Published prices

1–3 / 3

minimax/h3-lite ↗

$0.03

Inference provider
cloudflareWorkersAI
Platform
minimax
Unit
second
Currency
USD
Billing conditions
Billing label
Default (per second)
Pricing via
Cloudflare AI Gateway

minimax/h3-lite ↗

$0.03

Inference provider
cloudflareWorkersAI
Platform
minimax
Unit
second
Currency
USD
Billing conditions
label
@480p (per second)
Billing label
@480p (per second)
Pricing via
Cloudflare AI Gateway

minimax/h3-lite ↗

$0.04

Inference provider
cloudflareWorkersAI
Platform
minimax
Unit
second
Currency
USD
Billing conditions
label
@768p (per second)
Billing label
@768p (per second)
Pricing via
Cloudflare AI Gateway

Provider specifications & access

1–1 / 1

MiniMax H3 Lite ↗

source model id
minimax/h3-lite
hosting
third-party
platforms
  • minimax
architecture
input_modalities
  • text
  • image
  • video
  • audio
output_modalities
  • video
capabilities

    Original sources

    1–2 / 2

    GitHub · Source snapshot ↗

    Cloudflare AI · Catalog ↗

    Source links

    1–1 / 1

    Explore more models

    Models

    Loading
    EVIDENCE / COMPARISON

    Benchmarks

    Explore every benchmark

    Loading

    These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

    Install TensorTrace