AI video generator: text, image and reference to video

Makernice is an AI video generator you can use in the browser console or through one API key. It runs 13 video models from ByteDance, MiniMax, Alibaba and Kuaishou for text to video, image to video, reference to video and first and last frame. Every run is quoted before it starts, and video is billed per second.

Makernice Team · Updated November 2, 2026

How do you make an AI video on Makernice?

Use the web console for a few clips without code, or the API for apps and batches. Both use the same models, the same prices and the same prepaid balance.

In the browser (no code)

Sign in and top up your prepaid balance (from $15; it never expires).
Open Create → Video, pick a model and a mode, then write a prompt and add images if the mode needs them.
The price appears before you press Generate. Download the clip when it's ready; finished files are kept for about 30 days.

Open the video console

With the API

Quote: POST /v1/generations/quote returns the exact amount, holds nothing and locks the price for 12 minutes.
Create: POST /v1/generations with the quote_id, the same input and an Idempotency-Key header. The quoted amount is held from your balance.
Poll GET /v1/generations/{id} until status is succeeded, or add a top-level callback_url to get a webhook. Then download outputs[0].url.

Quickstart · Webhooks · No charge for failed generations

curl https://api.makernice.com/v1/generations/quote \
  -H "Authorization: Bearer $MAKERNICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"seedance-2.5","mode":"t2v","prompt":"A slow dolly shot through a greenhouse","duration":5,"resolution":"720p"}'

curl https://api.makernice.com/v1/generations \
  -H "Authorization: Bearer $MAKERNICE_API_KEY" \
  -H "Idempotency-Key: 7c1e9a2b-order-1842" \
  -H "Content-Type: application/json" \
  -d '{"quote_id":"qt_…","input":{"model":"seedance-2.5","mode":"t2v","prompt":"A slow dolly shot through a greenhouse","duration":5,"resolution":"720p"}}'

curl https://api.makernice.com/v1/generations/gen_… \
  -H "Authorization: Bearer $MAKERNICE_API_KEY"

What kinds of AI video can Makernice generate?

Four modes, set with the mode field: text to video, image to video, reference to video and first and last frame. Each model supports some or all of them; the table shows which, and every model's page has its full specs.

Catalog facts from GET /v1/models. Full comparison with audio and prices: Models.
Model	Text	Image	Reference (max images)	First and last frame	Duration
Seedance 2.5	Yes	Yes	16	Yes	4–30 s
Seedance 2.0	Yes	Yes	9	Yes	4–15 s
Seedance 2.0 Fast	Yes	Yes	9	Yes	4–15 s
MiniMax H3	Yes	Yes	5	Yes	5–15 s
MiniMax H3 Max	Yes	Yes	4	Yes	5–15 s
MiniMax H3 Max Turbo	Yes	Yes	—	Yes	5–15 s
Wan 3.0	Yes	Yes	10	Yes	2–30 s
Wan 3.0 Prime	Yes	Yes	10	Yes	2–30 s
Kling 3.0 Pro	Yes	Yes	—	Yes	3–15 s
Kling 3.0 Standard	Yes	Yes	—	Yes	3–15 s
Kling 3.0 4K	Yes	—	—	—	3–15 s
Kling 4.0	Yes	Yes	10	Yes	3–30 s
Happy Horse 1.1	Yes	Yes	9	—	3–15 s

Catalog facts from GET /v1/models. Full comparison with audio and prices: Models.

Text to video

Write a prompt with mode t2v; no image needed. All 13 video models support it and accept aspect_ratio in this mode, and Kling 3.0 4K does text to video only. Text-to-video prompt tips

Image to video

Send one still as the first frame with mode i2v and image_url. 12 of the 13 video models support it; Kling 3.0 4K does not. Image to video on Makernice: models, steps and prices

Reference to video

Send several images in reference_images with mode r2v to keep a character, product or style consistent without fixing any frame. 9 of the 13 video models support it, with up to 16 on Seedance 2.5; 10 on Wan 3.0, Wan 3.0 Prime and Kling 4.0; 9 on Seedance 2.0, Seedance 2.0 Fast and Happy Horse 1.1; 5 on MiniMax H3; 4 on MiniMax H3 Max. Reference-to-video guide

First and last frame

Send image_url for the opening frame and last_image_url for the closing frame with mode flf; the model generates the motion between them. 11 of the 13 video models support it, all except Kling 3.0 4K and Happy Horse 1.1. Fields and supported models

How much does a 5- or 10-second AI video cost on Makernice?

A 10-second text-to-video clip at each model's default resolution costs from $0.48 on MiniMax H3 Max Turbo to $5.14 on Kling 3.0 4K (price list v12, November 2, 2026). Higher resolutions cost more per second; every model's page lists its price per resolution.

From GET /v1/pricing, at each model's default resolution. Totals are rounded to the cent; your quote shows the exact amount before you run anything. Live rates: Pricing. MiniMax H3: 480p, 768p native · 2K, 4K upscaled from 768p.
Model	Resolution	Per second	5 s clip	10 s clip
Seedance 2.5	720p	$0.2592/s	$1.30	$2.59
Seedance 2.0	720p	$0.1704/s	$0.85	$1.70
Seedance 2.0 Fast	720p	$0.1027/s	$0.51	$1.03
MiniMax H3	2K	$0.156/s	$0.78	$1.56
MiniMax H3 Max	768p	$0.0685/s	$0.34	$0.69
MiniMax H3 Max Turbo	768p	$0.048/s	$0.24	$0.48
Wan 3.0	720p	$0.0789/s	$0.39	$0.79
Wan 3.0 Prime	720p	$0.1234/s	$0.62	$1.23
Kling 3.0 Pro	1080p	$0.1612/s	$0.81	$1.61
Kling 3.0 Standard	720p	$0.1209/s	$0.60	$1.21
Kling 3.0 4K	4K	$0.5142/s	$2.57	$5.14
Kling 4.0	720p	$0.168/s	$0.84	$1.68
Happy Horse 1.1	720p	$0.168/s	$0.84	$1.68

From GET /v1/pricing, at each model's default resolution. Totals are rounded to the cent; your quote shows the exact amount before you run anything. Live rates: Pricing. MiniMax H3: 480p, 768p native · 2K, 4K upscaled from 768p.

Prices as of November 2, 2026 (price list v12).

Frequently asked questions

Is the Makernice AI video generator free?

No. There is no free tier, no free credits and no subscription. You top up a prepaid US dollar balance, $15 to $1,000 per top-up, and the balance never expires. Getting a quote costs nothing and holds nothing.

Can one Makernice API key do text to video, image to video and reference to video?

Yes. All 13 video models share one request shape: set mode to t2v, i2v, r2v or flf, and change the model field to switch models. Same key, same balance, same quote, create and poll flow. GET /v1/models lists the modes each model supports.

Which Makernice video models make clips longer than 15 seconds?

Seedance 2.5 (4 to 30 seconds), Wan 3.0 (2 to 30 seconds), Wan 3.0 Prime (2 to 30 seconds) and Kling 4.0 (3 to 30 seconds). The other video models stop at 15 seconds. Video is billed per second of the duration you request.

What is the difference between reference to video and image to video on Makernice?

Image to video uses one image as the first frame. Reference to video (mode r2v) takes several images in reference_images, up to 16 on Seedance 2.5, to keep a character, product or style consistent without fixing any frame. 9 of the 13 video models support it.

Does Makernice charge for a failed AI video generation?

No. Creating a run holds the quoted amount. If the generation fails, times out or is canceled while queued, the hold is released in full. Quality is not a failure condition: a delivered video is charged, whatever you think of it. Note: if a finished output is blocked by output moderation for a policy violation, the run is still charged. You can contact support for a manual review.

Image to video · AI image generator · All models · Pricing · No charge for failed generations