Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Kitani offers a cloud-based AI inference platform that allows developers to utilize API access for open-weight language models, community fine-tunes, and image-generation models without the need for managing model-serving infrastructure. It features an endpoint that is compatible with OpenAI, enabling chat and text generation, which includes capabilities for streaming and tool utilization on supported models, making it easy for developers to integrate SDKs and related software simply by adjusting the endpoint and credentials. Additionally, Kitani includes a comprehensive model catalog, API keys, and tools for usage tracking, along with a pay-as-you-go pricing structure based on specific model rates. The Kitani One subscription plan is available on a monthly basis, providing access to features within designated model allowances and usage caps. Comprehensive setup guides are available to assist users in developing coding agents and chat interfaces, which support a variety of platforms such as Cline, Continue, Open WebUI, LibreChat, and OpenCode. The service caters to a diverse range of applications, from enhancing apps with model-generated responses to offering coding support, fostering creative writing, and generating images; the extent of these capabilities is determined by the chosen model. Overall, Kitani streamlines the process of leveraging advanced AI tools for developers, enabling innovative solutions across multiple domains.
Description
Run BiOS offers a serverless and OpenAI-compatible inference solution that allows you to direct the OpenAI SDK towards its endpoint, enabling you to maintain your existing code. It features six model families—Claude, DeepSeek, GLM, Kimi, MiniMax, and Qwen—alongside a bios-adaptive system that optimizes each request for quality, speed, and budget while adhering to a specified price ceiling. Both prompts and responses are temporarily stored in memory and removed once the request is fulfilled, ensuring there are no request logs, content stores, or archives retained. Additionally, fine-tuning and dedicated GPU endpoints can be accessed under the same account if you later decide to obtain ownership of the weights, with billing occurring per second of GPU usage. The pricing structure is based on your consumption from a prepaid balance, calculated per million tokens, and the endpoint will pause instead of accumulating debt if your balance depletes.
API Access
Has API
Yes
API Access
Has API
No
Screenshots View All
No images available
Screenshots View All
No images available
Integrations
Aider
Yes
Cline
Yes
Continue
Yes
Jan
Yes
Kilo Code
Yes
LibreChat
Yes
Open WebUI
Yes
OpenCode
Yes
Roo Code
Yes
SillyTavern
Yes
Integrations
Aider
No
Cline
No
Continue
No
Jan
No
Kilo Code
No
LibreChat
No
Open WebUI
No
OpenCode
No
Roo Code
No
SillyTavern
No
Pricing Details
$5/month
The API is pay as you go, with model-specific input, output, and cached-input rates per million tokens; image generation is $0.01 per image. Kitani One starts at $5 per month and includes plan-specific models and shared five-hour and weekly usage allowances. One keys do not fall back to PAYG.
Free Trial
No
Free Version
No
Pricing Details
No price information available.
Free Trial
Yes
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
Kitani
Country
United States
Website
kitani.ai/
Vendor Details
Company Name
UltraSafe AI Inc.
Founded
2025
Country
United States
Website
runbios.ai