Explore and use powerful models
We provide API-based inference across leading models, including text generation, image generation, and more.
ShuttleAI Auto
Smart request router that dynamically chooses the best model for tasks.
GPT-5
Latest iteration in the GPT-5 series with further improvements.
Claude Opus 4.6
Anthropic's most intelligent model for building agents and coding.
Why choose ShuttleAI?
There are many reasons to choose ShuttleAI, but here are some of the most important ones.
Fast Infrastructure
Affordable
Reliable
Launch in seconds
Simple pricing, powerful models
One subscription. All the top-tier models you need through a single API.
Free
Try it out with open-source models
- GPT-OSS 20B & GPT-OSS 120B
- Up to 2 requests per minute*
- 8K context window
- Community support
Basic
Access faster, more capable models
- Everything in Free, plus:
- GPT-5.2 & Claude Haiku 4.5
- Up to 10 requests per minute*
- 16K context window
Premium
Unlock the most powerful models
- Everything in Basic, plus:
- Claude Opus 4.6 & Claude Sonnet 4.6
- Up to 30 requests per minute*
- 36K context window
Scale
For production workloads & teams
- Everything in Premium, plus:
- All models including beta access
- Up to 80 requests per minute*
- 128K context window
Everything you need to know about ShuttleAI. Can't find the answer you're looking for? Feel free to contact our support team.
ShuttleAI is a unified API platform that provides access to leading AI models including GPT-5, Claude 4, and many others. We make it easy to integrate powerful AI capabilities into your applications.
We offer transparent, usage-based pricing. Choose from our Free, Basic, Premium, or Scale plans. You only pay for what you use with no hidden fees or surprise charges.
We choose to focus on quality over quantity. We only offer the best, most reliable models that meet our high standards for performance and cost-efficiency. Our library is curated to ensure you have access to top-tier AI capabilities without the noise of less effective options.
Yes! We provide comprehensive API documentation with examples, SDKs, and guides to help you get started quickly. Visit our docs portal for detailed information.
Rate limits vary by plan: Free (2 req/min), Basic (10 req/min), Premium (30 req/min), and Scale (80 req/min). Enterprise customers can get custom limits.
Yes! Our Free plan includes 1000 free requests per month, access to core models, and community support. It's a great way to try out ShuttleAI.
Absolutely! We provide email support for all users, priority support for Premium and Scale customers, and dedicated support for Enterprise clients.
Yes, each plan has specific usage limits. Premium models have multiplier limits compared to standard models. See our pricing page for full details.
The Free plan is available to individuals and small projects. You need to sign up with a valid email address and verify your credit card (we won't charge you).
