Near AI Cloud Integrates with OpenAI for Private Computation

Near AI Cloud has achieved OpenAI compatibility for developers, making it easier to redirect existing OpenAI client code to Near's infrastructure by changing one URL and swapping in a Near AI API key.

The Near AI Cloud API supports both chat completions and legacy completions endpoints, covering the majority of production OpenAI integrations. It also supports tool calling and structured outputs, with routing architecture directing requests through a central gateway or directly to model-specific endpoints running inside Trusted Execution Environments (TEEs).

Near's TEE-hosted models, including GLM 5.2 variants, run inside Intel TDX combined with NVIDIA confidential computing hardware. Every request carries a complete attestation, which is a cryptographic proof that the computation happened inside a genuine secure enclave and was not tampered with.