MiniMax H3
MiniMax H3 video generation supports text-to-video, image-to-video (first frame or first/last frames), and reference-to-video using text, images, audio and video. Output: 768P, with audio generated by default. Billed by successfully generated duration at a list price of CNY 0.50/second; promotional pricing is shown on the page. Failed generations are not billed. Reference images, audio and video inputs are temporarily free.
Supply channels
Multiple compute channels with automatic failover when a channel is rate limited or unavailable.
Channels are ordered by request volume over the last 24 hours. A valid public provider name is shown when available; otherwise a generic channel label is used. Availability, latency and throughput use a rolling 24-hour window. Hourly colors show operational, degraded, down or no-traffic periods. Hover for actual values. The price is the same across channels.
Quick start
OpenAI compatible asynchronous tasks: submit, poll the status, then download the completed video.
import time
from openai import OpenAI
client = OpenAI(
base_url="https://api.goodputai.cn/v1",
api_key="GOODPUT_API_KEY",
)
# Submit an asynchronous generation task
video = client.videos.create(
model="minimax/h3",
prompt="Sunrise by the sea, waves breaking on rocks, cinematic camera movement",
# Omit size for the model default canvas; see /docs/video-generation for options
seconds="5",
)
# Poll the task status, then download the completed video
while video.status in ("queued", "in_progress"):
time.sleep(5)
video = client.videos.retrieve(video.id)
if video.status == "completed":
client.videos.download_content(video.id).write_to_file("output.mp4")Billing method：Billed by generated duration: CN¥0.09 per second.Prices shown include the discount. Official list price: CN¥0.50 per second.
Related models
MiniMax H3: text/image/reference-to-video (first or first/last frames), with text/image/audio/video inputs. 768P; audio on by default. List CNY 0.50/s; promo price on page. Failures unbilled; reference inputs temporarily free. Fast: pull-mode queue; submit returns task id. Only 1344x768 (16:9, default) or 768x1344 (9:16); 5–14s (default 5s). Frame rounding may add up to ~0.7s; billed by requested seconds. Other parameters match H3.
GLM-5.3 is the next-generation model in Z.AI's GLM series, supporting up to 1M context tokens and 128K output tokens. Native deep thinking, tool calling and structured output support long-document understanding, code generation and complex reasoning. Served on our own compute infrastructure, with both OpenAI and Anthropic API protocols.
Add MiniMax H3 to your app
Change the base URL and start calling after you sign up.