Build with AI for less
The lowest-cost API on the market for image, video, audio, 3D and LLMs. Fully PAYG at the best rates in the industry, no contracts, better rate limits. Access raw GPU compute to run your own inference workloads at 50% lower cost.
Serverless and compute
Raw GPU and CPU compute billed by the second. Run your own inference workloads with no infrastructure to manage, and reserve capacity for the lowest rates.
| Profile | Memory / class | Per second | Per hour |
|---|---|---|---|
vCPU node | CPU service profile | $0.0000044 | $0.016 |
RTX PRO 6000Launch | 96 GB GDDR7 | $0.000553 | $1.99 as low as $0.99 |
H100 | 80 GB HBM | $0.000767 | $2.76 |
H200 | 141 GB HBM3e | $0.000883 | $3.18 |
B200 | Premium reserved | $0.001386 | $4.99 |
B300 | Premium reserved | Custom | Custom |
On-demand model APIs
Fully managed, pay-as-you-go inference across 400K+ models for image, video, audio, 3D and LLMs. No cold starts, no servers to run.
Pricing varies across thousands of parameters. The table above shows popular models and common configurations. To see the exact cost for any request, open the model in the Playground.
View full model directoryGet in touch
Questions about pricing, volume discounts, or running at scale? Send us a message and we'll get back to you as soon as possible.
Tell us about your workload and we'll figure out the best setup with you.
Frequently Asked Questions
Pricing & Billing
What is Runware and what can I do with it?
Runware is an AI-as-a-Service platform that provides access to thousands of AI models for image, video, audio, LLM, 3D generation, and utility tasks through a simple API.
How does pricing work?
We use a pay-as-you-go model. You only pay for what you use, with pricing varying by model and parameters like resolution, duration, and quality settings.
Can I see models from the global Diffusion marketplace?
Yes, we integrate with various model marketplaces to provide you access to the latest and most popular models.
Will Runware scale with my needs?
Absolutely. Our infrastructure is built to scale automatically, handling everything from small experiments to production workloads generating millions of assets.
Can I get volume discounts?
Yes, we offer volume discounts for high-usage customers. Contact our sales team to learn more about custom pricing.
Technical
Does my usage count if I get rate-limited?
No, you're only charged for successful API requests that generate outputs.
Is there a free trial or credit to test with?
Yes, new users receive $2 in free credits to explore our platform and test various models.
What kind of image generation costs can I expect?
Image generation typically ranges from $0.0006 to $0.24 per image depending on the model, resolution, and quality settings.
How do I know which model to use?
Each model has different strengths. Check our documentation for detailed comparisons, or start with our popular models.
Account & Support
Are my uploaded models kept private?
Yes, any custom models or content you upload remain completely private and are never shared or used for training.
Can I get custom discounts for high volume?
Yes, we offer volume discounts for enterprise customers. Contact our sales team to discuss your needs.
Does Runware scale with my needs?
Yes, our platform automatically scales to meet your demand, whether you're generating 10 or 10 million images.
Does this apply to legacy models?
Legacy models may have different pricing. Check the individual model pages for specific details.
Models & Features
Which models are included?
We provide access to thousands of AI models for image generation, video generation, audio synthesis, 3D generation, and utility tasks.
Can I use my own models?
Yes, you can import and run your own custom models on our platform.