close
Skip to main content
NEAR AI Cloud provides access to leading AI models, each optimized for different use cases ranging from advanced reasoning and tool calling to long-context processing, embeddings, reranking, image generation, and audio transcription — all with transparent, pay-per-use pricing. The catalog contains two kinds of models:
  • TEE-hosted models (marked TEE) run on NEAR AI’s own GPU fleet inside Trusted Execution Environments. They support attestation, signatures, and verification, are reachable through direct completions endpoints, and nobody — not even NEAR — can see your prompts or outputs.
  • Third-party models (OpenAI, Anthropic, Gemini, and others) are proxied to their providers through the NEAR AI gateway for convenience. They offer the same unified API and billing, but the TEE privacy and verifiability guarantees do not extend to the upstream provider.
Browse Model Catalog →
Model metadataThe /v1/models endpoint reports each model’s context length, max output length, pricing (including discounted cache-read pricing — see Prompt Caching), supported features (tools, structured_outputs, reasoning), supported sampling parameters, and input/output modalities.