Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Confidential AI offers a secure platform for private AI inference, agent environments, and confidential computing solutions tailored for AI laboratories, inference service providers, routers, and organizations that manage sensitive data. Its hosted inference service operates open-weight models within hardware-backed trusted execution environments (TEEs), utilizing technologies such as Intel TDX and AMD SEV-SNP confidential virtual machines, paired with NVIDIA GPUs in a confidential computing configuration. The system ensures that prompts, responses, and workload information remain safeguarded from infrastructure operators, allowing clients to authenticate attestation prior to submitting sensitive information. Users have the flexibility to implement an OpenAI-compatible API to establish inference endpoints and agent workloads, or alternatively, they can acquire the confidential-computing stack for deployment on their own premises, bare metal servers, or across major cloud platforms. This service is particularly beneficial for scenarios that involve serving models while restricting operator access to prompts and model assets, as well as executing sensitive AI workloads in a dedicated confidential computing environment. Additionally, the emphasis on robust security measures fosters trust in the processing of sensitive data, enabling clients to focus on innovation without compromising privacy.
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.
API Access
Has API
Yes
API Access
Has API
Yes
Screenshots View All
No images available
Screenshots View All
No images available
Integrations
Aider
No
Cline
No
Continue
No
Jan
No
Kilo Code
No
LibreChat
No
Open WebUI
No
OpenAI
Yes
OpenCode
No
Roo Code
No
Integrations
Aider
Yes
Cline
Yes
Continue
Yes
Jan
Yes
Kilo Code
Yes
LibreChat
Yes
Open WebUI
Yes
OpenAI
No
OpenCode
Yes
Roo Code
Yes
Pricing Details
$0.30 per 1M input tokens
Confidential Inference (OpenAI-compatible API, per 1M tokens):
DeepSeek V4.1 Flash (live): $0.30 input, $0.03 cached input, $1.20 output.
Kimi K3 (on request): $3.00 input, $0.30 cached input, $15.00 output.
GLM 5.3 (on request): $1.40 input, $0.26 cached input, $4.40 output.
Qwen3.8 27B (on request): $0.30 input, $0.03 cached input, $1.80 output.
DeepSeek V4 Flash is no longer offered; DeepSeek V4.1 Flash is the current live model.
Confidential GPU VMs (per GPU-hour, confidential computing mode):
NVIDIA B300: $7.50 (available).
NVIDIA B200: $6.50 (available).
NVIDIA H100: $3.25 (on request).
CPU VMs: $0.05 per core-hour plus $0.012 per GB-hour (AMD SEV-SNP and Intel TDX).
Licensed stack (per GPU per year): RTX PRO 6000 $2,789; H100 $3,876; H200 $4,974; B200 $7,625; B300 $9,884. CPU core license $48.85 per core per year. Standard support included; Enterprise support 25% of total license price.
Terms: minimum order $500. 50% on signed order, 50% on completion; monthly in arrears for longer engagements. USD by bank transfer (ACH or international wire). Card payments coming soon.
DeepSeek V4.1 Flash (live): $0.30 input, $0.03 cached input, $1.20 output.
Kimi K3 (on request): $3.00 input, $0.30 cached input, $15.00 output.
GLM 5.3 (on request): $1.40 input, $0.26 cached input, $4.40 output.
Qwen3.8 27B (on request): $0.30 input, $0.03 cached input, $1.80 output.
DeepSeek V4 Flash is no longer offered; DeepSeek V4.1 Flash is the current live model.
Confidential GPU VMs (per GPU-hour, confidential computing mode):
NVIDIA B300: $7.50 (available).
NVIDIA B200: $6.50 (available).
NVIDIA H100: $3.25 (on request).
CPU VMs: $0.05 per core-hour plus $0.012 per GB-hour (AMD SEV-SNP and Intel TDX).
Licensed stack (per GPU per year): RTX PRO 6000 $2,789; H100 $3,876; H200 $4,974; B200 $7,625; B300 $9,884. CPU core license $48.85 per core per year. Standard support included; Enterprise support 25% of total license price.
Terms: minimum order $500. 50% on signed order, 50% on completion; monthly in arrears for longer engagements. USD by bank transfer (ACH or international wire). Card payments coming soon.
Free Trial
Yes
Free Version
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
Deployment
Web-Based
Yes
On-Premises
Yes
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)
Yes
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)
Yes
In Person
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Confidential AI
Founded
2025
Country
United States
Website
confidential.ai
Vendor Details
Company Name
Kitani
Country
United States
Website
kitani.ai/
Product Features
Virtual Machine
Backup Management
No
Graphical User Interface
No
Remote Control
No
VDI
No
Virtual Machine Encryption
No
Virtual Machine Migration
No
Virtual Machine Monitoring
No
Virtual Server
No