MiniMax API v1
September 25, 2024 (August 6, 2026)
This is experimental API for for the MiniMax AI, a Chinese AI startup backed by Alibaba and Tencent.
We provide full API support for following MiniMax/Hailuo AI models:
- MiniMax videos supports 19 models across 5 families: Hailuo 01/02/2.3, Hailuo 3.0, Veo 3.1, Sora 2, and Seedance 2.0 Standard/Fast/Mini. These models are notable for generating ultra-realistic video clips with precise prompt following.
- MiniMax images supports 9 models: Midjourney V7, Midjourney NiJi 7, Nano Banana 2, Nano Banana Pro, GPT Image 1.5, GPT Image 2, Seedream 4.5/5.0, and image-01.
- MiniMax agent supports multiple AI models including video generation (Hailuo 2.3, 02, Veo 3.1, Sora 2), image generation (Midjourney V7/NiJi 7, Nano Banana 2/Pro, Seedream 4.5/5.0, Kontext, Qwen, Kolors), and audio synthesis (Speech 2.5, Music 2.0).
Nano Banana 2/Pro deployment provided by MiniMax has less content moderation compared to Google Flow and is capable of editing photos of minors or famous people.
💲 Credits estimator
Actual costs may change, see hailuoai.video for current pricing. The $ at Master column prices each generation on the $79.99/m Master plan ($0.00762/credit, the lowest cost per credit). Paid plans apply Seedance 2.0 at half credits, already reflected below.
Seedance 2.0 and Hailuo 3.0 bill per second, and a video reference is charged on its own length on top of the generated clip — at a lower per-second rate than the output. Image and audio references carry no per-second charge. The calculator below takes a video reference length so you can see the full cost.
| Plan | Monthly | Credits/mo | $/credit |
|---|---|---|---|
| Standard | $9.99 | 1,000 | $0.00999 |
| Pro | $34.99 | 4,500 | $0.00778 |
| Master | $79.99 | 10,500 | $0.00762 |
| Max | $199.99 | 20,000 | $0.01000 |
Images — per image, see images/create for details
| Model | Credits | $ at Master |
|---|---|---|
| image-01 | 1 | $0.008 |
| midjourney-v7, midjourney-niji7 | 3 | $0.023 |
| seedream-4.5, seedream-5.0 | 4 | $0.030 |
| nano-banana-2 (512P/1K) | 4 | $0.030 |
| nano-banana-2 (2K) | 5 | $0.038 |
| nano-banana-2 (4K) | 8 | $0.061 |
| nano-banana-pro (1K/2K) | 6 | $0.046 |
| nano-banana-pro (4K) | 10 | $0.076 |
| gpt-image-1.5 (Low/Medium/High) | 4 / 8 / 15 | $0.030 / $0.061 / $0.114 |
gpt-image-2 quality low (1K/2K/4K) | 2 / 5 / 10 | $0.015 / $0.038 / $0.076 |
gpt-image-2 quality medium (1K/2K/4K) | 8 / 20 / 40 | $0.061 / $0.152 / $0.305 |
gpt-image-2 quality high (1K/2K/4K) | 30 / 80 / 160 | $0.229 / $0.609 / $1.219 |
Videos — see videos/create for details
Billed per second, so multiply by your duration (4–15). A video reference is charged on its own length as well, at the rate in the last column — image and audio references add nothing per second.
| Model | Resolution | Credits/sec | Video ref/sec | $ at Master, per sec |
|---|---|---|---|---|
| Hailuo-3.0 | 768p | 7 | 7 | $0.053 |
| Hailuo-3.0 | 2K | 12 | 12 | $0.091 |
| Seedance-2.0 | 480p | 10 | 6 | $0.076 |
| Seedance-2.0 | 720p | 21 | 14 | $0.160 |
| Seedance-2.0 | 1080p | 50 | 30 | $0.381 |
| Seedance-2.0 | 4K | 100 | 60 | $0.762 |
| Seedance-2.0-Fast | 480p | 8 | 4 | $0.061 |
| Seedance-2.0-Fast | 720p | 17 | 11 | $0.130 |
| Seedance-2.0-Mini | 480p | 5 | 3 | $0.038 |
| Seedance-2.0-Mini | 720p | 11 | 7 | $0.084 |
Billed per video, at a fixed price per option.
| Model | Option | Credits | $ at Master |
|---|---|---|---|
| Hailuo 01 (all models) | — | 25 | $0.190 |
| Hailuo 02, T2V-2.3, I2V-2.3 | 768p / 1080p | 25–80 | $0.190–$0.609 |
| I2V-2.3-Fast | 768p / 1080p | 15–50 | $0.114–$0.381 |
| Sora-2 | 4 / 8 / 12 sec | 40 / 80 / 120 | $0.305 / $0.609 / $0.914 |
| Veo-3.1, Veo-3.1-S2V | 720p / 1080p / 4K | 120 / 120 / 180 | $0.914 / $0.914 / $1.371 |
| Veo-3.1-Fast, Veo-3.1-S2V-Fast | 720p / 1080p / 4K | 60 / 60 / 90 | $0.457 / $0.457 / $0.686 |
Interactive calculator — pick a plan and model for the per-generation cost:
Estimate only — it does not include any discounts or promotional pricing. Plan rates are the current published monthly prices.
Postman collection (August 6, 2026)
LLM-friendly API spec Feed this to your LLM to build integrations
Q&A: How is your experimental MiniMax API different from the official MiniMax API?
Blogs:
- MiniMax H3 vs Seedance 2.0: 2K with native audio, head to head
- Seedance 2.0: Standard vs Fast vs Mini, omni references
- 17 AI Image Models: The Showdown
- Nano Banana 2
- Midjourney V7: prompts, image references, and pricing
- MiniMax Sora 2 & Midjourney V7
- MiniMax Sora 2, Veo 3.1
- MiniMax Agent: Nano Banana 2/Pro, Speech 2.5, Music 2.0 and more…
- MiniMax 2.3
- MiniMax 02 End Frame
- Groundbreaking Video Agents
- MiniMax Images
Articles:
Developer Community:
Table of contents
-
GETaccounts -
GETaccounts/account -
POSTaccounts -
DELaccounts/account -
GETfeatures -
POSTvideos/create -
POSTvideos/agent-create -
GETvideos/videoId -
GETvideos -
GETvideos/agent-templates -
GETvideos/characters -
POSTvideos/cancel -
DELvideos/videoId -
POSTimages/create -
GETimages -
GETimages/imageId -
DELimages/imageId -
POSTagent -
GETagent/jobId -
GETagent/jobs -
POSTfiles -
GETfiles -
DELfiles/fileID -
GETscheduler -
GETscheduler/available -
DELscheduler/id