15% off all sale models
Create API key

OPEN HIGGSFIELD API

Sign up for 15% off all sale models - then raise your favorites up to 50%, plus $15 on your balance. Your first result is minutes away

Create API keyGet 50% discount

Integration

CONNECT ONCE. BUILD ANYTHING.

1const res = await fetch(2  'https://api.higgsfield.ai/bytedance/seedance-2.0/text-to-video', {3    method: 'POST',4    headers: {5      Authorization: `Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}`,6      'Content-Type': 'application/json',7    },8    body: JSON.stringify({9      prompt: 'A cinematic tracking shot along a sunlit coastal road',10      resolution: '720p',11      generate_audio: true,12      duration: 5,13      aspect_ratio: '16:9',14    })15  }16)
Explore all

Model catalog

THE MODELS YOU NEED, ALL IN ONE PLACE.

Seedance 2.5
30% OFF
Seedance 2.5

Generates videos from text, images, video, and audio references, with optional audio generation. Supports videos up to 30 seconds with customizable resolution, aspect ratio, and output format.

Video0.144/ s$0.2057
Genjutsu
50% OFF
Genjutsu

Transforms existing videos using image references for different characters, locations, and styles, preserving the original motion, camera movement, and timing throughout the resulting video clip.

Video0.159/ s$0.318
Kling 3.0
45% OFF
Kling 3.0

Generates multi-shot videos from text or images, with native audio and durations up to 15 seconds.

Video0.0462/ s$0.084
MiniMax H3
30% OFF
MiniMax H3

Generates 2K videos up to 15 seconds using text, image, video, and optional audio reference files.

Video0.091/ s$0.13
Wan 3.0 Prime
30% OFF
Wan 3.0 Prime

Generates videos from text or media references with fast processing and clips up to 30 seconds.

Video0.0476/ s$0.068
Marketing Studio Image
Marketing Studio Image

Generates and edits campaign images from text and image inputs, with resolutions from 1K to 4K. Preset mode uses a product photo and an optional model reference to guide the resulting image.

Image0.0126/ image
Explore all models

7-DAY LAUNCH OFFER

PICK ANY 4 MODELS. SAVE UP TO 50%

Create API keySave up to 50%
Model name
  1. Seedance 2.530% off
  2. Genjutsu50% off
  3. Kling 3.045% off
  4. MiniMax H330% off
  5. Wan 3.0 Prime30% off
  6. Marketing Studio Image
  7. Seedance 2.030% off
  8. Cinema Studio 4.0
  9. Grok Imagine 2.0
  10. Soul 2
  11. Genjutsu50% off
  12. Wan 3.050% off
  13. LTX 2.5 Fast
  14. LTX 2.5 Pro
  15. Grok Imagine Video 1.5
  16. Wan 2.750% off
  17. Happy Horse 1.130% off
  18. Ideogram 4.0
  19. Recraft 4.1
  20. Happy Horse 1.030% off
  21. PixVerse 615% off
  22. Kling O345% off
  23. Kling 2.645% off
  24. Kling O1 (Omni)45% off
  25. Wan 2.650% off
  26. MiniMax Hailuo 2.375% off
  27. Kling 2.545% off
  28. Soul Standard
  29. Cinema Studio 4.0
  30. Qwen Image 3
  31. Z-Image Turbo
  32. Product shots
  33. Graphic ads
  34. Marketplace design

Ideas to build

Don't start from a blank page

Content factory

Write one line about your product and get a creator-style video with the script, presenter, and voice ready.

Fashion photoshoots

A full photoshoot without the studio. Consistent AI models wear your products in your brand's style - shot, retouched, and e-commerce ready in minutes, not weeks

Explore all models
Fashion photoshoots

Cinematic pipeline

Your idea, now in motion. Turn a short creative brief into a polished cinematic sequence without a production crew, expensive equipment, or weeks of post-production.

Works with your existing stack

Teams already using fal or Replicate can switch by swapping a single key and keep the rest of their code in place.

FAL_KEY
REPLICATE_API_TOKEN
ELEVENLABS_API_KEY
HIGGSFIELD_API_KEY

1 week offer

Sign up and save up to 50%

Create API key
30% OFF
Seedance 2.5

Generates videos from text, images, video, and audio references, with optional audio generation. Supports videos up to 30 seconds with customizable resolution, aspect ratio, and output format.

Video0.144/ s$0.2057
50% OFF
Genjutsu

Transforms existing videos using image references for different characters, locations, and styles, preserving the original motion, camera movement, and timing throughout the resulting video clip.

Video0.159/ s$0.318
45% OFF
Kling 3.0

Generates multi-shot videos from text or images, with native audio and durations up to 15 seconds.

Video0.0462/ s$0.084
30% OFF
MiniMax H3

Generates 2K videos up to 15 seconds using text, image, video, and optional audio reference files.

Video0.091/ s$0.13
30% OFF
Wan 3.0 Prime

Generates videos from text or media references with fast processing and clips up to 30 seconds.

Video0.0476/ s$0.068
Marketing Studio Image
Marketing Studio Image

Generates and edits campaign images from text and image inputs, with resolutions from 1K to 4K. Preset mode uses a product photo and an optional model reference to guide the resulting image.

Image0.0126/ image
30% OFF
Seedance 2.0

Creates 4K video from text or media references. Supports up to 15 seconds with optional sound.

Video0.0985/ s$0.1407
Cinema Studio 4.0

Generates cinematic videos from text, image, or video references with automatic scene direction. Supports videos up to 30 seconds, optional sound, and customizable resolution and aspect ratio.

Video0.2057/ s

Analytics

See where every dollar goes

Track spend by day, model, and workflow, with discounts shown on your invoice. Pick a period, export the CSV, and send it to finance.

Get started

Three steps from key to content

Read the docs
  1. 1

    Configure credentials

    export HF_API_KEY_ID="your-api-key-id"export HF_API_KEY_SECRET="your-api-key-secret"
  2. 2

    Submit a generation

    curl --request POST \  --url https://api.higgsfield.ai/bytedance/seedance-2.0/text-to-video \  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" \  --header "Content-Type: application/json" \  --data '{    "prompt": "A cinematic tracking shot along a sunlit coastal road",    "resolution": "720p",    "generate_audio": true,    "duration": 5,    "aspect_ratio": "16:9"  }'
  3. 3

    Check the result

    curl --silent --show-error --fail-with-body \  --url "https://api.higgsfield.ai/requests/${REQUEST_ID}/status" \  --header "Authorization: Key ${HF_API_KEY_ID}:${HF_API_KEY_SECRET}" | jq

The whole Higgsfield engine, one key away

One key unlocks 24 frontier models, the playground, and a week of welcome discounts. Your first result is minutes away

Create API keySave up to 50%

Community over 25 MILLION USERS

Join a global creative network where people generate AI images, share ideas, and inspire each other every day.

I've been using Higgsfield for my creative work for a while now and, honestly, it's one of the best platforms out there - the tools are powerful and the results speak for themselves. But what made me write this was the support. I had a question about my credits, and Tim handled everything with a transparency and care you rarely see.

Im a new customer of Higgsfield and enjoying it! I'm making some cool videos. I look forward to the advances on the platform! Oh, the support service is excellent!

Higgsfield A.I. has been the best and most exciting tool I've used since I first started editing back in 2008! I still can't believe we live in a time where we can type a sentence; prompt, on one end and get a blockbuster video that comes out on the other end! The site can feel overwhelming at times, but in a good way.

I am an Indonesian content creator based on my experience, I feel helped by the presence of this AI Agent higgsfield I say honestly and swear also thank you.. Because AI Agent Higgsfield has helped a lot, especially for creators in the form of our full support to create. In addition to this support, there are many other supports that are very helpful, especially the Higgsfield team

What Higgsfield is doing really well is making high-quality AI creation feel smooth, fast, and inspiring. I also appreciate how the company supports its creative community and gives artists the freedom to experiment, grow, and push visual storytelling to the next level.

The user interface (UI) is highly intuitive and beginner-friendly. Additionally, the cloud rendering speed for generating both images and videos is exceptionally fast, and the AI tools menu is very well-organized. I have completed numerous projects using Higgsfield, and every single one of them turned out perfectly.

For a long time, I have seen it as a useful and well-optimized tool, designed to help creators in the best possible way. I like that it constantly introduces updates and interesting features that improve the experience. That is why it has always been a platform that has caught my attention and that I have enjoyed using compared to others.

Honestly one of the best AI creative platforms out there. The credit pricing is surprisingly affordable compared to similar platforms, and what impresses me most is how consistently they keep shipping new features. You can tell the team actually listens and keeps pushing the product forward.

The Most Powerful AI Creative Platform for Creators. What impressed me the most is the level of support around the creator program. The team is helpful, professional, and always there when you need assistance or have questions. It really feels like they care about creators and want to help them grow.

Trusted by 5.000+ people worldwide

Still have questions?

We’ve answered the most frequently asked questions

What is Higgsfield API?
One key that unlocks 50+ frontier models for image, video, and audio. You send a prompt, we handle the queueing, GPUs, and scaling — you get back a URL.
How does pricing work?
Pay per generation, no subscriptions and no seats. Every model's price is public in the catalog, so you know what a job costs before you run it, and volume discounts apply automatically as usage grows.
What's in the launch offer?
Sign up and get 15% off all models by default. Pick any 4 more models to raise the discount up to 50%, verify your business email and add a card for $15 on your balance, and your first API key comes with 20 concurrent requests.
Do I need to talk to sales to start?
No. The playground is free, and a key takes minutes to create. Sales is only for monthly commitments and custom volume terms.
How hard is the integration?
Three calls: POST the model's endpoint with your prompt, get back a request_id with a status_url, poll it until completed — the response carries the file URL. JavaScript, Python, and cURL examples sit side by side in the docs.
I'm already using fal or Replicate. What do I have to rewrite?
Nothing structural — the flow is the same shape: submit, poll, fetch. Most teams switch by swapping a single key in their env.
Can my AI agent use it?
Yes — that's built in. Every model page has a "Copy for agent" setup, there's an MCP server for Claude Code and Cursor, and the docs are published in an agent-readable format.
What are the rate limits?
You start with 20 concurrent requests per key. Raising limits is a settings change, not a manual review — reach out when you need more.
How do I keep spend under control?
Analytics shows spend by day, model, and workflow with discounts visible on the invoice, and exports to CSV for finance. Auto top-up keeps pipelines running; any job can be stopped early via its cancel_url.
How do teams work?
Personal and team workspaces share one balance and one invoice. Keys are per project — rotate or revoke in one click.
Which models are included?
The catalog covers the top image, video, and audio models — Seedance, Kling, Veo, GPT Image, Soul, VoiceLab and more — and new ones land the day they ship, on the same endpoint, no code changes.