
by NEAR AI
NEAR AI Cloud is a private AI inference platform that runs open-weight models inside hardware enclaves and returns a signed proof with each response. It uses an OpenAI-compatible API.
APIUsage-based
Step 1: Create an API key in the NEAR AI Cloud console.
Step 2: Point an OpenAI-compatible client at the NEAR AI base URL.
Step 3: Pick a model from the catalog and send requests.
Step 4: Verify the attestation and response signature using the verification docs.
Step 5: Set a spend cap on each key and watch usage per key.
A Trusted Execution Environment is a hardware-isolated region of a CPU or GPU where code and data stay encrypted while running. The host, operator and NEAR AI cannot read your prompts.
No. Pay-as-you-go is billed per token with no minimums or subscriptions, and attestation is included in the rate.
No. The API is OpenAI-compatible, so you change the base URL and keep your existing code.
Enterprise agreements add reserved GPU capacity, private models, volume pricing with SLAs and on-prem or VPC deployment.
Cloudflare AI GatewayCloudflare AI Gateway sits between your application and AI model providers. It adds analytics, logging, caching, rate limiting, routing with fallbacks and safety controls, and takes one line of code to start.
GitGuardianGitGuardian finds leaked secrets and machine credentials across code, CI/CD, collaboration tools and developer machines, then helps teams route, rotate and close each incident. It is available as SaaS or self-hosted.MemoryGuard MCPMemoryGuard is a local-first MCP memory server for coding agents. It organizes what agents write, keeps evidence for changes and lets governance decisions be rolled back.