| Confidential AI | bf16.ai | |||||
|---|---|---|---|---|---|---|
Related Products
|
||||||
Confidential AI:
About
Confidential AI provides private inference, private agents, confidential VMs and confidential computing infrastructure for AI labs, inference providers, routers, and organizations handling sensitive workloads. Its hosted inference service runs open-weight models in hardware-backed trusted execution environments (TEEs), including Intel TDX and AMD SEV-SNP confidential VMs with NVIDIA GPUs in confidential computing mode. Prompts, responses, and workload data are protected from infrastructure operators, and clients can verify attestation before sending sensitive input. Customers can use an OpenAI-compatible API to deploy inference endpoints and agent workloads, or license the confidential-computing stack for on-premises infrastructure, bare metal, and major clouds. Use cases include serving models while limiting operator access to prompts and model assets, and running sensitive AI workloads on dedicated confidential compute.
|
bf16.ai:
About
bf16.ai is a hosted large language model API and inference service for developers building coding assistants and autonomous agents. It serves edited open-weight models, including DeepSeek, GLM, and Kimi families, through OpenAI-compatible Chat Completions and Responses endpoints and an Anthropic-compatible Messages endpoint. Selected models offer tool use, vision, and context windows up to one million tokens. Developers can connect documented coding and agent clients such as Claude Code, Codex CLI, OpenCode, and OpenClaw, or test requests in the web Playground. Usage is billed per token from a prepaid balance, with rates varying by model and token type; introductory account credit is available for testing. bf16.ai states that it does not retain prompts or completions after processing. Use cases include software development, agent orchestration, security testing, browser automation, and research.
|
|||||
Confidential AI:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
bf16.ai:
Platforms Supported
Windows
Not Supported
Mac
Not Supported
Linux
Not Supported
Cloud
Supported
On-Premises
Not Supported
iPhone
Not Supported
iPad
Not Supported
Android
Not Supported
Chromebook
Not Supported
|
|||||
Confidential AI:
Audience
AI labs, inference providers, routers and regulated companies.
|
bf16.ai:
Audience
Software developers, AI engineers, DevSecOps teams, and indie hackers building coding agents and autonomous workflows.
|
|||||
Confidential AI:
Support
Phone Support
Not Supported
24/7 Live Support
Supported
Online
Supported
|
bf16.ai:
Support
Phone Support
Not Supported
24/7 Live Support
Not Supported
Online
Supported
|
|||||
Confidential AI:
API
Offers API
Supported
|
bf16.ai:
API
Offers API
Supported
|
|||||
Confidential AI:
Screenshots and VideosNo images available
|
bf16.ai:
Screenshots and VideosNo images available
|
|||||
Confidential AI:
Pricing
$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.
Free Version
Not Supported
Free Trial
Supported
|
bf16.ai:
Pricing
$0.26/1M input tokens
Pay-as-you-go, prepaid in USD, with no monthly subscription; rates vary by model and token type and start at $0.26 per 1M input tokens. Top-ups are $10–$2,000 and purchased balance does not expire. New accounts receive $0.20 in trial credit, valid for 30 days; no payment card is required.
Free Version
Not Supported
Free Trial
Supported
|
|||||
Confidential AI:
Reviews/
|
bf16.ai:
Reviews/
|
|||||
Confidential AI:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Supported
In Person
Supported
|
bf16.ai:
Training
Documentation
Supported
Webinars
Not Supported
Live Online
Not Supported
In Person
Not Supported
|
|||||
Confidential AI:
Company InformationConfidential AI
Founded: 2025
United States
confidential.ai
|
bf16.ai:
Company Informationbf16.ai
Founded: 2026
Singapore
bf16.ai
|
|||||
Confidential AI:
Alternatives |
bf16.ai:
AlternativesNo Alternatives
|
|||||
| Confidential AI: | ||||||
| Confidential AI: | ||||||
| Confidential AI: | ||||||
|
Confidential AI:
|
bf16.ai: | |||||
Confidential AI:
Categories |
bf16.ai:
Categories |
|||||
Confidential AI:
Integrations
Claude Code
Not Supported
Codex CLI
Not Supported
Goose
Not Supported
Kilo Code
Not Supported
OpenAI
Supported
OpenClaw
Not Supported
OpenCode
Not Supported
Zed
Not Supported
|
bf16.ai:
Integrations
Claude Code
Supported
Codex CLI
Supported
Goose
Supported
Kilo Code
Supported
OpenAI
Not Supported
OpenClaw
Supported
OpenCode
Supported
Zed
Supported
|
|||||
|
Confidential AI:
|
bf16.ai:
|