Simple and transparent pricing

Pay only for what you use. No hidden fees, no surprises. Scale from prototype to production with confidence.

Image & Video Models

Generate stunning images and videos with state-of-the-art AI models. Billed per image, video second, or megapixel depending on the model.

Image Generation

ModelUnitPriceOutput per $1
Nano Banana Proimage$0.147 images
Seedream V4.5image$0.0425 images
Flux Dev Ultra Fastimage$0.005200 images
Z-Imageimage$0.005200 images

Video Generation

ModelUnitPriceOutput per $1
Sora 2second$0.110 seconds
Veo 3.1second$0.43 seconds
Wan 2.2 Ultra Fastsecond$0.0120 seconds
InfiniteTalksecond$0.0333 seconds

* Pricing may vary based on resolution, duration, and generation complexity. Video pricing calculated per second or per video.

Language Models

Access powerful language models for text generation, analysis, and more. Billed per token (1K tokens ≈ 750 words).

ModelContext WindowInput PriceOutput Price
Gemini 3 Pro Preview128K tokens$0.002/1K tokens$0.012/1K tokens
GPT-5.2128K tokens$0.00175/1K tokens$0.014/1K tokens
Claude Opus 4.5200K tokens$0.005/1K tokens$0.025/1K tokens
Qwen3 Max128K tokens$0.0012/1K tokens$0.006/1K tokens

* Input and output tokens are billed separately. 1K tokens is approximately 750 words.

Serverless GPU

Deploy your own models on enterprise-grade GPU infrastructure. Pay only for compute time with per-second billing.

GPUVRAMPrice per hourPrice per second
B2
B200
141GB$5.98$0.0017
H2
H200
80GB$3.59$0.001
H1
H100 PRO
80GB$2.29$0.0006
A1
A100
48GB$1.39$0.0004
A6
A6000
32GB$1.69$0.0005
50
5090
24GB$0.69$0.0002

* GPU pricing includes compute, memory, and networking. Custom configurations and dedicated instances available.

Learn more

For a deeper dive, check out how billing works on our platform.

Enterprise & volume discounts

If you need more support or have complex requirements, we can offer:

Dedicated account manager

Get personalized support from a dedicated team member who understands your needs.

Priority support

Fast-track your requests with priority access to our engineering team.

Higher GPU limits

Scale without constraints with increased GPU allocation and concurrent processing.

Performance SLAs

Guaranteed uptime and performance with enterprise-grade service level agreements.

Help with onboarding, custom models, and optimizations

Expert guidance to help you deploy custom models, optimize performance, and get the most value from our platform.

Volume discounts available

We've got volume discounts for large amounts of spend. Contact our enterprise team to learn more about custom pricing.

Ready to get started?

Join thousands of developers building the next generation of AI applications.

No credit card required • Start with $1 free credits