Deep Infra
1.0 out of 5 starsAverage Ratings 3 Ratings
Average Ratings 0 Ratings
Description
Experience a robust, self-service machine learning platform that enables you to transform models into scalable APIs with just a few clicks. Create an account with Deep Infra through GitHub or log in using your GitHub credentials. Select from a vast array of popular ML models available at your fingertips. Access your model effortlessly via a straightforward REST API. Our serverless GPUs allow for quicker and more cost-effective production deployments than building your own infrastructure from scratch. We offer various pricing models tailored to the specific model utilized, with some language models available on a per-token basis. Most other models are charged based on the duration of inference execution, ensuring you only pay for what you consume. There are no long-term commitments or upfront fees, allowing for seamless scaling based on your evolving business requirements. All models leverage cutting-edge A100 GPUs, specifically optimized for high inference performance and minimal latency. Our system dynamically adjusts the model's capacity to meet your demands, ensuring optimal resource utilization at all times. This flexibility supports businesses in navigating their growth trajectories with ease.
Description
Featherless is a provider of AI models, granting subscribers access to an ever-growing collection of Hugging Face models. With the influx of hundreds of new models each day, specialized tools are essential to navigate this expanding landscape. Regardless of your specific application, Featherless enables you to discover and utilize top-notch AI models. Currently, we offer support for LLaMA-3-based models, such as LLaMA-3 and QWEN-2, though it's important to note that QWEN-2 models are limited to a context length of 16,000. We are also planning to broaden our list of supported architectures in the near future. Our commitment to progress ensures that we continually integrate new models as they are released on Hugging Face, and we aspire to automate this onboarding process to cover all publicly accessible models with suitable architecture. To promote equitable usage of individual accounts, concurrent requests are restricted based on the selected plan. Users can expect output delivery rates ranging from 10 to 40 tokens per second, influenced by the specific model and the size of the prompt, ensuring a tailored experience for every subscriber. As we expand, we remain dedicated to enhancing our platform's capabilities and offerings.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
Llama
Yes
Llama 2
Yes
Llama 3
Yes
Llama 3.1
Yes
Llama 3.2
Yes
Llama 3.3
Yes
AI SpendOps
Yes
ChatGPT
No
Code Llama
Yes
Codestral
Yes
Integrations
Llama
Yes
Llama 2
Yes
Llama 3
Yes
Llama 3.1
Yes
Llama 3.2
Yes
Llama 3.3
Yes
AI SpendOps
No
ChatGPT
Yes
Code Llama
No
Codestral
No
Pricing Details
$0.70 per 1M input tokens
Free Trial
Yes
Free Version
No
Pricing Details
$25/month
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Deep Infra
Website
deepinfra.com
Vendor Details
Company Name
Featherless AI
Founded
2023
Country
United States
Website
featherless.ai/
Product Features
Machine Learning
Deep Learning
No
ML Algorithm Library
No
Model Training
No
Natural Language Processing (NLP)
No
Predictive Modeling
No
Statistical / Mathematical Tools
No
Templates
No
Visualization
No