Compare Plans & Features
Find the perfect plan to accelerate your AI deployment pipeline.
Developer$0 | Pro$499 / month | Business$1,999 / month | EnterpriseCustom Annual Contract | |
|---|---|---|---|---|
| Target Audience | ||||
| Audience | Individuals & students | Startups & small teams | Mid-size companies | Large-scale & specialized |
| Core Offering | ||||
| Monthly Engine Builds | 10 Builds | 100 Builds | 500 Builds | Unlimited / Custom |
| Model Source | Public Models Only | Private Model Uploads | Private Model Uploads | Private Model Uploads |
| Max Model Size | 2 GB | 10 GB | 20 GB | Unlimited |
| Build Concurrency | 1 | 2 | 5 | Dedicated Build Fleet |
| Target Hardware Platforms | ||||
| Cloud & Server GPUs | ✓ (NVIDIA Standard) | ✓ (NVIDIA Standard) | ✓ (NVIDIA Latest Gen) | ✓ (Full NVIDIA & AMD Catalog) |
| Cloud & Server CPUs | - | - | Beta Access (Intel OpenVINO) | ✓ (Full Intel OpenVINO Support) |
| Mobile NPUs | - | - | Beta Access (Apple CoreML) | ✓ (Apple, Qualcomm, Google, Samsung) |
| High-Performance Edge | - | - | ✓ (NVIDIA Jetson) | ✓ (NVIDIA Jetson, Qualcomm Robotics, etc.) |
| Embedded & TinyML | - | - | - | ✓ (Microcontroller Targets) |
| Engine Output Formats | ||||
| Server Engine File | ✓ (.plan) | ✓ (.plan) | ✓ (.plan, .xml+.bin) | ✓ (All Server Formats) |
| Mobile Package | - | - | ✓ (.mlpackage) | ✓ (All Mobile Formats) |
| Embedded Library | - | - | - | ✓ (Self-Contained C++ Library / C-Array) |
| Features & Integrations | ||||
| ONNX Ingestion | ||||
| TensorRT Engine Output | ||||
| Performance Benchmarks | ||||
| Team Members | Up to 10 users | Up to 25 users | Unlimited Users | |
| CI/CD Integration (API) | Full API Access | Full API Access | ||
| Advanced Quantization | ✓ (Standard INT8) | ✓ (+ Custom Datasets) | ✓ (+ Multiple Algorithms) | ✓ (+ Integer-Only INT8/INT4 for MCUs) |
| Memory & Performance Simulators | - | - | ✓ (For Server GPUs) | ✓ (+ RAM/Flash Estimates for TinyML) |
| Enterprise & Vertical Solutions | ||||
| Professional Services | - | - | - | ✓ (Access to Custom Kernel Development) |
| Embedded Firmware SDKs | - | - | - | ✓ (Integration help for specific MCUs) |
| Custom Hardware Integration | - | - | - | ✓ (Bring-your-own-silicon program) |
| Security & Support | ||||
| Support | Community | Standard Email (48h SLA) | Priority Support (24h SLA) | Dedicated Slack & Account Manager |
| Security | Standard | Standard | SSO & Audit Logs | SSO, SOC 2, Security Reviews |
| Deployment & Advanced | ||||
| Target Hardware Profiles | Standard NVIDIA GPUs (e.g., T4, V100) | Standard NVIDIA GPUs | + Latest Gen GPUs (e.g., H100) | + Custom & Embedded Hardware (e.g., Jetson) |
| On-Premise Deployment | Available (Air-gapped option) | |||
| Direct xTorch Integration | Available | |||
| Custom Engineering | Access to Custom Kernel Development | |||
| Start for Free | Start Free Trial | Start Free Trial | Contact Sales | |
Question & Answerer
We answer your questions
XTorch is a command-line tool and Python library designed to streamline the conversion of PyTorch models into optimized TensorRT engines. It intelligently handles the conversion to ONNX and then to TensorRT, applying optimizations like FP16 or INT8 quantization to maximize inference speed.
No, but it is highly recommended. Ignition-Hub accepts any valid TensorRT
.engine file. If you have your own complex conversion pipeline, you can absolutely use that. XTorch is provided to make the process easier and more reliable for the 90% of use cases.XTorch is designed to work with models from PyTorch 1.8 and newer. We always recommend using the latest stable version of PyTorch for the best results, as ONNX export support improves with each release.
- FP16 (Half Precision): This optimization reduces your model's size by half and can significantly speed up inference with minimal loss in accuracy. It's a great default choice.
- INT8 (8-bit Integer): This offers the highest performance boost and smallest model size but requires a calibration step with a representative dataset. It can sometimes lead to a noticeable drop in accuracy, so it should be used carefully and validated. XTorch provides tools to help with the calibration process.
XInfer is our official client library (SDK) for interacting with models deployed on Ignition-Hub. It simplifies the process of making API requests by handling authentication, data serialization, and response parsing for you, so you can focus on your application logic.
Currently, we have official SDKs for Python and C++. We also provide clear REST API documentation for developers who wish to make requests from other languages like JavaScript, Go, or Rust.
Yes. Every model deployed on Ignition-Hub has a standard REST API endpoint. You can use any HTTP client, like
curl or Python's requests library, to call it. XInfer is simply a convenience wrapper.XInfer is a pure inference client. It does not perform pre-processing (like image resizing or normalization) or post-processing (like non-maximum suppression). This logic should remain in your application code for maximum flexibility. You prepare your input tensor, pass it to the XInfer client, and receive the raw output tensor(s) back.
Testimonials
Trusted by 1000+ companies
Dr. Lena Petrova
Lead AI Engineer at SynthVisionIgnition-Hub is a game-changer. We spent weeks trying to optimize our TensorRT engines for deployment, and the performance was still inconsistent. With Aryorithm, we just upload our model, and the inference API is not only fast but incredibly stable. We cut our deployment time by 80% and saw a 2x speedup on our core models.
David Chen
Founder & CEO of InsightFlow AnalyticsAs a startup, we can't afford a massive DevOps team or expensive GPU infrastructure. Ignition-Hub gave us enterprise-grade inference capabilities on a startup budget. The pay-as-you-go pricing is transparent, and it scales effortlessly as our user base grows. It’s the serverless backend for AI we've been dreaming of.
Maria Garcia
Indie DeveloperI was hitting a wall trying to deploy my custom computer vision project. Cloud GPU instances were too complex and expensive. I found Ignition-Hub, and within an hour, I had a live API endpoint for my TensorRT engine. The documentation is fantastic, and the user interface is so intuitive. It's the perfect platform for turning personal projects into real applications.
Our Client
15,000+ Professionals & Teams Choose Doodle
