All Providers

NEAR AI

Private, verifiable AI — Intel TDX + NVIDIA H200 TEE with on-chain attestation

NEAR AI Cloud runs inference inside Intel TDX confidential VMs backed by NVIDIA H200 Confidential Computing GPUs. TLS terminates inside the TEE (not at an external load balancer), so prompts are never exposed in plaintext outside the enclave. An optional E2EE layer lets clients encrypt messages with the model's attested public key before they leave the machine. Attestation reports are verifiable on-chain via the NEAR blockchain.

HQ San Francisco, CA
Models 4
From $0.15/M input tokens

API Features

OpenAI Compatible
Streaming
Function Calling
Batch Inference
Vision
Embeddings

Models & Pricing

Model Family Context Max Out Input /M Output /M Free
DeepSeek V3.1 DeepSeek 125K $1.05 $3.10
GPT-OSS 120B OpenAI GPT 128K $0.15 $0.55
Qwen3 30B A3B Qwen 256K $0.15 $0.55
GLM-5 FP8 ZhipuAI GLM 198K $0.85 $3.30