Authentication
Every request is authenticated with a bearer token in theAuthorization header. The API
accepts four token types; for programmatic access you almost always want an API key.
Chat Completions
The primary inference endpoint
Models
List models, context windows, and pricing
Attestation
Verify the TEE running your requests
POST /v1/responses is stateless and supports store: false only. Read the
Stateless Responses guide before migrating
an integration that uses conversations, files, response history, or built-in tools.New to NEAR AI Cloud? Start with the Quickstart, then see
OpenAI Compatibility for SDK setup details.